Program Guide SAS Global Forum 2012

Program Guide SAS Global Forum  2012
The information in this PDF is valid as of March 16.
SAS Global Forum 2012
Program Guide
Walt Disney World Swan and Dolphin Resort
Orlando, Florida | April 22-25, 2012
Andrew T. Kuligowski, Conference Chair
Information Hotline: 919-531-5001
Dear Fellow SAS Professionals:
As SAS Global Forum 2012 Conference Chair, I want to welcome you to my adopted home state and to Orlando, FL.
Thank you for joining us at SAS Global Forum!
I’m honored to share with you everything that makes this a unique and fantastic event each year: hands-on
demonstrations, thought-provoking keynote presentations, industry-specific workshops and more than 300 papers
and presentations highlighting the latest technology and industry solutions.
Be sure to check out the revised hours for the SAS Support and Demo Area this year, opening on Sunday from 4 to
6 p.m. Also, there will be a new experience called “SAS Backstage” that I’m sure you’ll find exciting. Taking place
Wednesday morning in the Atlantic Hall, it offers the opportunity for you to join the audience during a live “SAS
Talks” and engage in a roundtable discussion. Sign-up is available on Agenda Builder.
Andrew T. Kuligowski
2012 Conference Chair
The incredible program you’re about to enjoy was built by a dedicated team of volunteers who spent many hours
of time and effort. They have earned my sincere thanks and appreciation for a job well done; I’m proud to be
associated with each and every one of them.
I’d especially like to recognize all of you – the many SAS users who have made their way here from every corner of
the globe. The ideas, questions, challenges and solutions you bring with you, coupled with those you bring back
home, are what make SAS Global Forum the premier gathering of SAS users worldwide.
Finally, I thank our sponsors for their support: Accenture, HP, Teradata, Greenplum, Oracle, Red Hat, Experis, EMC
Isilion, Futrix, IBM, Platform Computing, Blue Star Infotech, ESRI, Metacoda, Modern Analytics, D-Wise, Qualex,
Texas A&M University, Saint Joseph’s University, NC State University, Oklahoma State University, University of
Central Florida, University of Alabama, United Global Solutions, Deloitte, Smith Hanley and Louisiana State University.
Please visit our sponsors in the SAS Support and Demo Area.
Conference highlights include:
• Opening Session – The official welcome to the conference by the SAS executive team.
• SAS Support and Demo Area – The best place to get direct access to developers.
• Technology Sections – Provide focus on SAS software use and programming, tips and techniques.
• Industry Solutions – Discover methods and technologies to solve specific business problems.
• The Technology Connection – See what’s on the horizon and provide feedback to SAS R&D.
• Closing Session – The traditional announcements and wrap-up will be augmented by a closing keynote from
noted SAS personality Chris Hemedinger.
Again, welcome – have a wonderful conference!
Andrew T. Kuligowski
Conference Chair
Lobby - Level 3 (Across from Asia 4 & 5)
Atlantic/Pacific Halls – Level 1
Saturday, April 21:
Sunday, April 22:
Monday, April 23:
Tuesday, April 24:
Wednesday, April 25:
Sunday, April 22:
Monday, April 23: Tuesday, April 24: Wednesday, April 25:
1:00 p.m. – 6:00 p.m.
7:00 a.m. – 6:30 p.m.
7:00 a.m. – 6:00 p.m.
7:00 a.m. – 6:00 p.m.
7:00 a.m. – 1:00 p.m.
4:00 p.m. – 6:00 p.m.
10:00 a.m. – 4:00 p.m.
10:00 a.m. – 5:00 p.m.
8:00 a.m. – 11:00 a.m.
Conference Chair Letter . . . . . . . . . . . Inside Front Cover
Quick Reference . . . . . . . . . . . . . . . . . . . Inside Front Cover
Things You Need to Know . . . . . . . . .
Page 2
• 11th Hour Business Center
• 2012 Children’s Book Drive
• Conference Program Guide
• First Timers' Session
• Internet Café
• Luggage Storage
• Meet Up Boards
• Proceedings
• Ribbons
• SAS BackStage
• SAS Global Forum Take Out
• Speaker Lounge
• Speaker Rehearsal Rooms
• Student and Faculty Lounge
• Tech Connecion
• WayFinder Kiosk
• Wireless Access
Schedule at a Glance . . . . . . . . . . . . . . Page 3
Keeping in Touch . . . . . . . . . . . . . . . . . .
Page 4
• Internet Café
• Latest updates from SAS Global Forum 2012
• Social Media
• Wireless Access
Networking Opportunities . . . . . . . .
Page 4
• Reception for Academic Attendees
• Opening Night Dinner
• Get–Acquainted Reception
• Lunch and Featured Presentation (Monday)
• Mixer hosted by SAS Customer Loyalty
• Lunch and Featured Presentation (Tuesday)
• Kick Back Party
Sessions/Abstracts . . . . . . . . . . . . . . . .
Page 5
• Sunday Pre-Conference Seminars
• Sunday Pre-Conference Statistical Tutorials
• Monday Abstracts
• Tuesday Abstracts
• Wednesday Abstracts
Index by Author . . . . . . . . . . . . . . . . . . . Page 73
Walt Disney World Swan and
Dolphin Resort
Outdoor Function Map . . . . . . . . . . . . Inside Back Cover
SAS Global Forum 2013 . . . . . . . . . . . Inside Back Cover
Walt Disney World Dolphin
Resort Conference Map . . . . . . . . . . . . Back Cover
Lobby - Level 3; outside Europe 4 & 5
Sponsored by the SAS Global Users Group, the 12th annual Children's Book
Drive benefits needy children in the Orlando area. Please bring your books to
the book drive table during the conference. The books will be distributed to
reading centers in shelters and community organizations in the area.
Located on Lobby - Level 3; outside Australia 3
All scheduled presentations contained within this book are current as of March
16, 2012. For the most up to date conference schedule please visit:
Tips & Tricks on how to navigate the conference. A must for the first time SAS
Global forum attendee. Hemisphere Ballrooms - Level 5; Southern Hemisphere; Room V.
Computers offering internet access are available for all attendees at the
Internet Café located on the Hemisphere Ballrooms - Level 5; Northern
Hemisphere Foyer AND Lobby - Level 3; across from Europe 3.
Luggage storage is available Wednesday ONLY on Lobby - Level 3;
Europe Room 2.
Lobby - Level 3; outside Asia 4
The Proceedings are available on the SAS Global Forum website.
Visit to view.
Conference attendees who have colored ribbons attached to their name
badges have special roles at the conference. These roles can be identified by
using the following ribbon key:
• SAS Global Users Group Executive Board – Forest Green
• Conference Chair – Purple • Section Chair – Maroon
• Special Event – Maroon • Session Coordinator – White
• Invited Speaker– Red • Contributed Speaker – Gold
• Partner – Light Blue • Sponsor – Black
• Press – Green • SAS Staff – Blue
Stick around on Wednesday for an up close and personal look into the
evolution of SAS - where we've been, where we're headed and how our
customers have helped shape the values, culture and success of SAS along the
way. – Atlantic/Pacific Halls - Level 1; SAS Support and Demo Area
SAS BACKSTAGE (continued)
SAS Interacts – Part of SAS BackStage
Join this intimate roundtable experience with SAS experts to hear about our
latest ideas, share information with other attendees or tell us what you think.
Sign up for the topic of your choice via the Agenda Builder. Seats are limited, so
claim yours now! Atlantic/Pacific Halls - Level 1; SAS Support and Demo Area
SAS Talks Live - Part of SAS BackStage
Wanted: Live Audience Members! Join the first live audience of SAS Talks
during SAS Global Forum, featuring technical presentations by SAS experts,
instructors and authors.
Atlantic/Pacific Halls - Level 1; SAS Support and Demo Area
If you missed key presentations, would like to revisit some of these presentations, were unable to attend the conference, or would like to share knowledge
from some popular papers with your colleagues, then you don’t want to miss
SAS Global Forum Take-Out! Back for a third year due to popular demand, SAS
users are offered a selection of video and audio presentations via the Internet.
This collection of presentations delivered by presenters at this year’s conference will be something that users will surely want to “take home” after the
conference. For more information visit
Lobby - Level 3; Oceanic Room 5
Lobby Level 3; Oceanic Rooms 3 & 4
Lobby - Level 3; Europe 7
Atlantic/Pacific Halls - Level 1; Pacific Hall
These self-service, interactive kiosks will be located throughout the conference
space, providing attendees with everything they need to know about what’s
happening at SAS Global Forum – from the latest announcements and social
media updates to details about training, papers, presentations, sponsor
locations, and SAS demos. There are four interactive kiosks located throughout
the conference. Locations are: Lobby – Level 3; Europe Hall; Atlantic/Pacific
Halls - Level 1; SAS Support and Demo Area and Hemisphere Ballrooms – Level 5.
Complimentary internet access is available during conference hours for all
attendees from Sunday, April 22 – Wednesday, April 25. Access is located on the
Hemisphere Ballrooms – Level 5 at the Internet Café ; Lobby – Level 3 at
the Internet Café and in the Atlantic/Pacific Halls - Level 1; SAS Support and
Demo Area.
SSID/Username = SASGlobalForum
Password = SASGlobalForum2012
Wednesday – Friday,
(April 18-20)
SAS Training Courses*
Saturday, April 21
1:00 p.m. – 6:00 p.m. . . . . . . . . . . . . . . . Registration
1:00 p.m. – 4:00 p.m. . . . . . . . . . . . . . . . SAS Certification*
Sunday, April 22
7:00 a.m. – 6:30 p.m. . . . . . . . . . . . . . . . .
8:00 a.m. – 4:00 p.m. . . . . . . . . . . . . . . . .
2:00 p.m. – 4:00 p.m. . . . . . . . . . . . . . . .
4:00 p.m. – 6:00 p.m. (New for 2012)
4:00 p.m. – 5:00 p.m. . . . . . . . . . . . . . . .
5:15 p.m. – 6:30 p.m. . . . . . . . . . . . . . . .
7:00 p.m. – 8:30 p.m. . . . . . . . . . . . . . . .
8:30 p.m. – 11:00 p.m. . . . . . . . . . . . . . .
Pre-Conference Activities*
Reception for Academic Attendees
SAS Support and Demo Area Open
First-Timers’ Session
Opening Night Dinner*
Opening Session
Get-Acquainted Reception
Monday, April 23
7:00 a.m. – 6:00 p.m. . . . . . . . . . . . . . . . .
8:00 a.m. – 10:00 a.m. . . . . . . . . . . . . . .
10:00 a.m. – 4:00 p.m. . . . . . . . . . . . . . .
10:30 a.m. – 5:50 p.m. . . . . . . . . . . . . . .
10:30 a.m. – 12:30 p.m. . . . . . . . . . . . . .
12:30 p.m. – 2:00 p.m. . . . . . . . . . . . . . .
2:00 p.m. – 3:30 p.m. . . . . . . . . . . . . . . .
2:00 p.m. – 4:00 p.m. . . . . . . . . . . . . . . .
6:00 p.m. – 7:30 p.m. . . . . . . . . . . . . . . .
6:00 p.m. – 8:00 p.m. . . . . . . . . . . . . . . .
Technology Connection & Keynote Presentation
SAS Support and Demo Area Open
Paper Presentations and Hands-On Workshops
Statistics and Data Analysis Keynote
Lunch and Featured Presentation*
Meet the Poster Authors – SAS Support and Demo Area
Beyond the Basics Keynote
Mixer Hosted by SAS Customer Loyalty
Tuesday, April 24
7:00 a.m. – 6:00 p.m. . . . . . . . . . . . . . . . .
8:00 a.m. – 5:30 p.m. . . . . . . . . . . . . . . . .
10:00 a.m. – 5:00 p.m. . . . . . . . . . . . . . .
12:00 p.m. (noon) – 1:30 p.m. . . . . . . .
6:00 p.m. – 8:00 p.m. . . . . . . . . . . . . . . .
9:00 p.m. – 1:00 a.m. . . . . . . . . . . . . . . . .
Paper Presentations and Hands-On Workshops
SAS Support and Demo Area
Lunch and Featured Presentation*
Kick Back Party
Wednesday, April 25
7:00 a.m. – 1:00 p.m. . . . . . . . . . . . . . . . .
8:00 a.m. – 12:00 p.m. (noon) . . . . . . .
8:00 a.m. – 11:00 a.m. . . . . . . . . . . . . . .
11:00 a.m. – 12:00 p.m. (noon). . . . . .
12:00 p.m. (noon) – 1:00 p.m. . . . . . . .
Paper Presentations and Hands-On Workshops
NEW – “SAS BackStage” – SAS Support & Demo Area
Statistics and Data Analysis Keynote
Closing Session
*Denotes Extra Fee Event
Computers offering internet access are available for all attendees at
the Internet Café located on the Hemisphere Ballrooms-Level 5;
Northern Hemisphere Foyer AND Lobby-Level 3; across from Europe 3.
Sunday, April 22, 2:00 p.m. - 4:00 p.m.
Academic attendees are invited to enjoy light refreshments and great
conversation in Americas Seminar room. Academic faculty and staff
are invited to attend and share career experiences with students and
junior faculty. Students are invited to attend and learn about different
career paths. We want to also learn how we can engage more
students, junior faculty and staff at SAS Global Forum each year.
Keep up to date with all the latest changes through an e-mail sent to
conference attendees each day. In addition, all the latest updates and
changes will be available on the wayfinder kiosks in the SAS Support
and Demo area, Level 3 (near the Internet Café) and Level 5 (near the
Information Center). Also, check out the SAS Users Groups Blog at for blogs on all the latest happenings and papers at the conference.
Continue your learning and networking opportunities all year long
with—the collaborative online community for SAS
users worldwide. Sponsored by the SAS Global Users Group Executive
Board, was created by SAS users for
SAS users. Here you can publish articles, upload
presentations, create a blog, find SAS code and join in
peer-to-peer discussions. You will find the “sasCommunity Tip of the Day” on the Main Page—and instructions
on how to sign-up to receive the Daily Tip via Twitter! With thousands
of registered members, the community continues to thrive and grow.
We invite you to explore and contribute to
SAS Global Forum is offering more opportunities than ever to
participate with conference social media and we want you to join the
conversation! Take advantage of the many ways to participate with
other attendees, contribute your thoughts, get frequent updates, and
learn the latest and greatest happenings at SAS Global Forum 2012.
Log on to the SAS Global Forum LinkedIn Group and connect online
with peers and presenters during the conference.
stay connected
Twitter—Handle: @SASGlobalForum and hashtag: #SASGF12
LinkedIn—SAS Global Forum 2012
SAS Global Forum Conference APP (for all smartphones) – Please visit
for complete information.
Complimentary internet access is available during conference hours
for all attendees from Sunday, April 22 – Wednesday, April 25. Access is
located on the Hemisphere Ballrooms – Level 5 at the Internet Café ;
Lobby – Level 3 at the Internet Café and in the Atlantic/Pacific Halls Level 1; SAS Support and Demo Area.
SSID/Username = SASGlobalForum
Password = SASGlobalForum2012
Sunday, April 22, 5:15 p.m. - 6:30 p.m.
Immediately before the Opening Session, meet your fellow conference
attendees over dinner on the Lake Terrace & Swan Pool located
outside of the Walt Disney World Swan Resort. *Extra fee item of $55
includes the cost of dinner. (This event is included in packages 2 & 3.)
Sunday, April 22, 8:30 p.m. -11:00 p.m.
Immediately following the Opening Session, come to the Get
Acquainted Reception to network with other attendees. The reception
is located on the Cabana Deck & Dolphin Pools located outside of the
Walt Disney World Dolphin Resort.
Monday, April 23, 12:30 p.m. -2:00 p.m. - Why SAS is an Institute
SAS is always breaking out of its shell to grow into the next bigger,
better idea for analytics. This is a retrospective, going back through
the experience of the first few shells we broke out of. *Extra fee item
$55.00. JOHN SALL (Co-founder and Executive Vice President, SAS)
Monday, April 23, 6:00 p.m.-7:30 p.m.
SAS serves as your host for this Monday evening mixer in the SAS
Support and Demo Area in the Atlantic/Pacific Halls – Level 1. This is
where we celebrate SAS users! Mingle and relax with other conference
attendees and enjoy some great food, drinks and fun entertainment.
Tuesday, April 24, 12:00 p.m. -1:30 p.m. - SAS Brings Analytics Center
Court with the Orlando Magic
With a new 875,000-square-foot, state-of-the-art arena, boasting the
latest in technology to enhance the fan experience, the Orlando Magic
use SAS to bring analytics center court. This session will highlight the
Magic's continued journey into analytics and how the use of SAS has
allowed the organization to better understand its customers and bring
a data-driven approach to moving its business forward. *Extra fee item
$55.00. ANTHONY PEREZ (Director of Business Strategy, Orlando Magic)
Tuesday, April 24, 9:00 p.m. -1 a.m.
Plan on “kicking back” while you enjoy drinks and a night of dancing
with your conference friends. This party is located on the Atlantic/
Pacific Halls – Level 1; Pacific Hall.
*Denotes Extra Fee Event
Walt Disney World Swan and Dolphin Resort
Andrew T. Kuligowski, Conference Chair
Featured Presenters
• Keynote Presentation
Monday, April 23, 8:00 a.m.
Game Plan for Success
Joe Theismann – Entrepreneur and former quarterback
for the Washington Redskins
• Lunch and Featured Presentation*
Monday, April 23, 12:30 p.m.
Why SAS is an Institute
John Sall – Co-founder and Executive Vice President, SAS
• Lunch and Featured Presentation*
Tuesday, April 24, 12:00 p.m.
SAS Brings Analytics Center Court
with the Orlando Magic
Anthony Perez – Director of Business Strategy, Orlando Magic
• Statistics and Data Analysis: Keynote 1
Monday, April 23, 10:30 a.m.
Handling Missing Data by Maximum Likelihood
Paul Allison – Professor of Sociology, University of Pennsylvania
• Statistics and Data Analysis: Keynote 2
Wednesday, April 25, 11:00 a.m.
Using SAS for the Design, Analysis, and
Visualization of Complex Surveys
Sharon L. Lohr – Dean’s Distinguished Professor of Statistics,
Arizona State University
• Beyond the Basics Keynote
Monday, April 23, 2:00 p.m.
Tales of 9.3: A Collection of Uses
David Shamlin – Senior Director, Research and
Development, SAS
• Closing Session Keynote
Wednesday, April 25, 12:00 p.m.
You Don’t Have to Go Home...
but You Can’t Stay Here
Chris Hemedinger – Principal Technical Architect, SAS
*Denotes extra-fee event
Pre-Conference Seminars — Northern
Hemisphere E-1
Pre-Conference Seminars — Northern
Hemisphere E-4
8:00 a.m.
8:00 a.m.
Best Practices in Base SAS® Coding
Brian Gayle, SAS
SAS® Administration: Understanding Architecture and
Gregory Nelson, ThotWave Technologies, LLC
Gordon Cox, Humana Inc.
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Seminars — Northern
Hemisphere E-2
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
8:00 a.m.
Pre-Conference Seminars — Northern
Hemisphere E-1
Excel VBA: When You Have to Step Outside SAS®
Peter Eberhardt, Fernwood Consulting Group Inc.
12:30 p.m.
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Seminars — Northern
Hemisphere E-3
8:00 a.m.
Innovative Tips and Techniques: Doing More in the
Art Carpenter, CA Occidental Consultants
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Building Powerful Reusable Tools with the SAS® Macro
Kirk Lafler, Software Intelligence Corporation
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Seminars — Northern
Hemisphere E-2
12:30 p.m.
Creating Complex Reports
Cynthia Zender, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Seminars — Northern
Hemisphere E-3
Pre-Conference Statistical Tutorials — Southern
Hemisphere IV
12:30 p.m.
10:30 a.m.
SAS® SQL: Building on the Basics
Davetta Dunlap, SAS
Data Simulation for Evaluating Statistical Methods in
Rick Wicklin, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Seminars — Northern
Hemisphere E-4
12:30 p.m.
Statistical Graphics Procedures and ODS GRAPHICS for
the Nonstatistician
Michele Ensor, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Statistical Tutorials — Southern
Hemisphere V
10:30 a.m.
Introduction to Bayesian Analysis Using SAS® Software
Maura Stokes, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Statistical Tutorials — Southern
Hemisphere IV
8:00 a.m.
Creating Statistical Graphics with ODS in SAS
Warren Kuhfeld, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Pre-Conference Statistical Tutorials — Southern
Hemisphere V
8:00 a.m.
SAS® Procedures for Analyzing Survey Data
Pushpal Mukhopadhyay, SAS
Please view the detailed abstract and schedule for this pre-conference
workshop at
sunday.html . SAS Global Forum Pre-Conference Workshops and Statistical
Tutorials are “extra-fee” events.
Walt Disney World Swan and Dolphin Resort
Andrew T. Kuligowski, Conference Chair
SAS Global Forum is offering more opportunities than ever to
participate with conference social media and we want you to join
the conversation! Take advantage of the many ways to participate
with other attendees, contribute your thoughts, get frequent updates,
and learn the latest and greatest happenings at SAS Global Forum
2012. Log on to the SAS Global Forum LinkedIn Group and
connect online with peers and presenters during the conference.
Twitter—Handle: @SASGlobalForum and hashtag: #SASGF12
LinkedIn—SAS Global Forum 2012
Applications Development — Southern
Hemisphere V
2:00 p.m.
How Readable and Comprehensible Is a SAS® Program?
A Programmatic Approach to Getting an Insight into a
Rajesh Lal, Experis
Raghavender Ranga, Vertex Pharmaceuticals
Paper 001-2012
In any programming language, there are general guidelines for writing
“better” programs. Well-written programs are easy to re-use, modify, and
comprehend. SAS programmers commonly have guidelines for indentation,
program headers, comments, dead code avoidance, efficient coding, etc. It
would be great if we could gauge a SAS program’s quality by quantifying
various factors and generalize for individual programming styles. This paper
aims to quantify various qualitative characteristics of a SAS program using
Perl regular expressions, and provide insight into a SAS program. This
utility, when used across a large project, can serve as a tool to gauge the
quality of programs and help the project lead take any corrective measures
to ensure that SAS programs are well written, easily comprehensible, well
documented and efficient.
2:30 p.m.
Macro Programming Best Practices: Styles, Guidelines
and Conventions Including the Rationale Behind Them
Don Henderson, Henderson Consulting Services
Art Carpenter, CA Occidental Consultants
(Invited) Paper 002-2012
Coding in the SAS Macro Language can be a rich and rewarding experience.
The complexity of the language allows for multiple solutions to many
programming situations. But which solution is best, is there even a "best"
solution, and how do you decide? Should you choose a technique based on
ease of programming or because of the efficiency of the solution? What is
the best practice for laying out your code, selecting your statements, and
organizing the way you use the symbol tables? Learn about macro
language programming styles, guidelines and conventions and why they
are important. Since not everyone always agrees on programming
practices, this paper will focus on the rationales behind the techniques so
you can make an informed choice based on your environment.
3:30 p.m.
Macro Design and Usage in A Multi-Tier Architecture for
ETL and Google Visualization API Integration
Manuel Figallo-Monge, DevTech Systems, Inc.
Paper 003-2012
A multi-tier architecture separates data management, application
processing, and presentation. This paper shows how to facilitate this
separation by producing loosely coupled, reusable macro components with
specified purposes that also interact with one another. It examines an ETL
batch file written so that one macro extracts XML files from a URL, a second
macro transforms the XML into SAS data sets, and another macro loads data
into memory objects. This data processing is extended with a presentation
layer macro, which integrates SAS® with the Google Visualization API to
produce a highly interactive motion chart that plays a dynamic movie to
explore several indicators over time. Ultimately, all of these SAS
components can be housed in a repository to be reused by developers in
an organization.
4:00 p.m.
Use the Full Power of SAS® in Your Function-Style
Michael Rhoads, Westat
Paper 004-2012
Function-style macros are macros that can be used within a SAS statement.
Although such macros are extremely flexible, they can only use macro
language code. So what do you do if you need a macro that can be
embedded within a SAS statement, but the underlying task requires the
execution of one or more DATA or PROC steps? You can now leverage the
capabilities of user-written SAS functions to circumvent this limitation,
meaning that your macros can now have the flexibility of a function-style
interface while still being able to execute one or more SAS steps in the
background. This paper describes the necessary techniques for developing
such macros and provides examples of situations where they can be most
4:30 p.m.
A Picture Is Worth a Lot of PUTs
Carol Martell, UNC Highway Safety Research Center
Paper 005-2012
This paper demonstrates the use of Picture formats to deliver SAS data to
nonstandard destinations, including a lengthy URL string, KML for Google
Earth, and ArcGIS.
5:00 p.m.
ODS PDF and RTF Application Development: Steps to
Ensure Success and Examples of Useful Coding
Benno Kurch, Trading and Software Development,
Paper 006-2012
For an ODS developer at a beginner or advanced level, creating tailor-made
ODS PDF or RTF reports is not an out of the box, turnkey operation.
Creating these reports can require thinking outside the box, however. For
example, implementing a larger font size when converting a listing report
to an ODS report might require report redesign and consultation with
business review personnel. This paper presents an overview of report
design techniques and a coding approach based on the use of the DATA
step, macro programming, and PROC REPORT. Taking time up-front to think
through potential issues can significantly reduce development time and
can help produce properly designed ODS reports that will impress users
with their professional look.
5:30 p.m.
Good Programming Practices: Creating Robust
Gregory Nelson, ThotWave Technologies, LLC
Jay Zhou, Amylin
Paper 417-2012
As part of a global initiative, the Good Programming Practices Executive
board, in collaboration with PhUSE and PharmaSUG, has begun developing
a set of standard practices that can be utilized throughout the industry. This
paper highlights one of those efforts to document best practices around
creating robust programs. Here, we talk about design patters helpful in
thinking about creating robust programs such as error proofing, test-first
design and defensive programming. From there, we outline some SAS®
programming techniques used in Base SAS® programming, SAS macros,
SQL, and in developing entire applications.
Applied Business Intelligence — Northern
Hemisphere A-4
10:30 a.m.
De Rigueur: Adding Process to Your Business Analytics
Falko Schulz, SAS
Diane Hatcher, SAS
Steve Sparano, SAS
Paper 019-2012
In an environment where there are multiple stakeholders involved in
delivering business analytics, process is required to establish “rigor,” a
check-and=balance system where reports and other analytic assets must be
verified and approved before being shared across the enterprise. Defining
an approval workflow is a common mechanism for implementing this
process. With the release of SAS® 9.3 Integration Technologies, your SAS
business analytics environment now includes the ability to define
workflows. This paper describe how to set up a report approval process
where reports are developed, submitted for approval, and then made
available in production (if approved). This process is managed via a custom
portlet surfaced through the SAS Portal, leveraging the new workflow
capabilities to track progress and execute batch SAS code.
11:30 a.m.
Lost in Wonderland? Methodology for a Guided DrillThrough Analysis Out of the Rabbit Hole
Stephen Overton, Zencos Consulting
Paper 020-2012
Business information can be consumed many ways using the SAS
Enterprise business intelligence platform. SAS® BI Dashboard can be used
to report high-level key performance indicators at-a-glance through the
SAS® Information Delivery Portal. Detailed Web-based reports can also be
surfaced from the SAS Information Delivery Portal through SAS® Web
Report Studio. This paper presents an information system that integrates
the functionality of these tools to answer business questions faster and
with a greater understanding of the key drivers of business-critical data.
This paper also presents the data infrastructure needed to support this type
of information system through the use of OLAP technology, effective data
architecture, report linking, and information maps.
12:00 p.m.
How to Create a Business Intelligence Strategy
Guy Garrett, Achieve Intelligence
Paper 021-2012
You may wonder how some organizations are so astute at managing to
keep abreast of changing customer behavior in the market. There are
undoubtedly many factors - however central to the answer is that they
recognize the value of their information assets and alter their strategic
vision with new perspective. A Business Intelligence Strategy is a roadmap
that enables businesses to measure their performance and seek out
competitive advantages and truly "listen to their customers" using data
mining and statistics. In this paper, you'll discover the crucial questions to
answer when aligning a BI strategy to your organization’s overall direction,
an overview of the artifacts to deliver, and how SAS® software can underpin
your strategy throughout the process.
2:00 p.m.
BI at Your Fingertips: Creating Immersive Mobile
Reports with SAS® Visual Designer
Scott McQuiggan, SAS
David Coyle, SAS
Gregory Thorne, SAS
Philippe Sabourin, SAS
Paper 022-2012
The pervasiveness of mobile computing has created a paradigm shift in
how information is consumed. It has become increasingly evident that
report consumers expect business intelligence to be readily available,
timely, and easily accessed wherever they are located. The new BI pipeline
from SAS® facilitates the distribution of information to the fingertips of
decision makers anywhere. In this paper, we offer best practices, tips, and
tricks for creating compelling, immersive reports for mobile BI users. Learn
how to transform a Web report into a mobile report using SAS® Visual
Designer and how to take advantage of features in the SAS® Mobile BI app
to delight and empower decision makers anywhere.
3:00 p.m.
The Emergence of Patterns in SAS® Usage and
Chuck Kincaid, Experis Business Analytics
Mike Vanderlinden, Experis
(Invited) Paper 023-2012
It used to be that there was one particular look and feel to a SAS
environment. Then platforms changed and editors changed, but for a long
time the infrastructure remained the same. With the introduction of a
comprehensive SAS® Business Intelligence Platform, the expansion of SAS
across the enterprise, and its integration with IT departments, new usage
patterns have emerged. More infrastructure choices are available to satisfy
the diverse roles required by companies that aim for analytics maturity. This
paper presents our analysis of the more prevalent patterns to date, and the
pros and cons of each. The interested audience could include IT and
business managers who are interested in the possible ways to deploy SAS
and what fits best for their environment.
4:00 p.m.
A New Outlook into Your Business
Anand Chitale, SAS
Mike Barnhart, SAS
Paper 024-2012
Business users rely on email for communication and collaborative decision
making. Have you ever wondered if you could use your Microsoft Outlook
environment beyond a simple communication tool and get added value
that keeps you more informed about your business? The integration of
SAS® into Microsoft Outlook provides a new outlook into your business.
This integration of SAS® Business Intelligence and Microsoft Outlook
increases informed decision making by giving business users intuitive
access to reports, stored processes, and dashboards. Business users obtain
contextual information from SAS Business Intelligence while performing
daily tasks in Microsoft Outlook. This paper highlights the key capabilities
provided by seamless integration of SAS with Microsoft Outlook and the
application of these capabilities available with SAS® Add-In for Microsoft
2:30 p.m.
4:30 p.m.
Paper 041-2012
Managing Multiple Languages with a Single Cube Using
SAS® 9.3
Tony Zhang, SAS
Ying Jin, SAS
Paper 025-2012
Global organizations manage business analysis efforts across a worldwide
corporate enterprise. These organizations are faced with building multiple
OLAP cubes that adhere to different cultural conventions. What if it were
possible to manage multiple languages and conventions within a single
cube? It can be done using SAS Unicode Server. Learn more about how
source data from the U.S., Japan, and China was integrated. Using SAS
Unicode Server, multiple languages came together within one cube. This
provided reusable reporting that could be adapted to meet region-specific
needs. Through global organizations, multiple languages are spoken but
within a single cube there is united business analysis.
Coders' Corner — Southern Hemisphere III
2:00 p.m.
One Flip, Two Flip, Fat File Flat File
Ethan Miller, SRI International
Paper 039-2012
Tired of getting data sets with multiple records per ID when you need a flat
file for analysis? Tired of struggling with one-too-many merges? With just a
small investment of time you too can easily create a flat file with one record
per ID. Through the use of PROC SORT, PROC TRANSPOSE, SAS® MACRO,
and the DATA STEP, this paper examines how to create a flat file with
customized variable names and labels for multiple time intervals. Through
the use of SAS MACRO, the code shown in this paper creates a flat file, and
your friends will be amazed at how easy it is. This paper was written for
those with beginner-to-intermediate skills; the code was written using SAS®
9.2 on a Windows operating system.
2:15 p.m.
Sometimes One Needs an Option with Unusual Dates
Arthur Tabachneck, myQNA
Matthew Kastin, I-Behavior, Inc.
Xia Shan, Chinese Financial Electrical Company
Paper 040-2012
Do you have date range analytical needs that you haven’t been able to
solve with the SAS® interval and holiday functions? You have if those needs
involved analyzing a date range that didn’t start at the beginning, end or
middle of a given month, involved holidays other than the US and Canadian
holidays that are incorporated in the holiday function, or if you had to
analyze data related to virtually any annual sporting event. This paper
shows how the intervalds option, introduced in SAS 9.2 phase 2, can be
used to meet such needs and includes code for addressing fiscal years in
Great Britain, Chinese, Hebrew and Islamic holidays, and for analyzing the
various rounds of the NCAA March Madness basketball tournament.
Andrea Wainwright-Zimmerman, Capital One
Have you ever had a data set that you were updating records in and you
needed to eliminate the old records and replace them with new records?
The SORT procedure with the NODUPKEY option eliminates rows that
duplicate your key fields, choosing which record to keep based on its own
logic, which might not be the one that you want. This paper shows how to
combine a PROC SORT and a DATA step to get the sorted data set with the
exact records that you want.
2:45 p.m.
Log Checks Made Easy
Yogesh Pande, Merck Sharp & Dohme Corp.
Paper 042-2012
It is Good Programming Practice (GPP) if a programmer checks SAS® log for
errors, warnings, and all other objectionable SAS NOTE. In order to
successfully create tables, listings, and figures, the programmer must
ensure that code is correct, and the accuracy of the code, assuming that the
program logic is correct, solely depends on SAS log. Using SAS macro
language and Base SAS®, this paper will introduce a macro that will enable a
programmer or statistician to check all SAS logs in a folder and tabulate the
log issues by the name of the SAS log file using PROC REPORT.
3:00 p.m.
It's Now Your Project—Clean It Up and Make It Shine
Leonard Polak, Wells Fargo Dealer Services
Paper 043-2012
Inherited projects may not be well designed. Though a new project owner
may not have time to upgrade substandard code immediately, most
inherited projects offer plenty of room for improvement. Developing
department or company standards and best practices, and then applying
these standards and best practices can result in code that is easy to
understand, easy to maintain, and easy to transition. The examples in this
paper are meant to promote improvements in productivity, consistency,
and clarity.
3:15 p.m.
Magic Spells with SAS®
Christopher Bost, MDRC
Paper 044-2012
Programmers often need to calculate spells, or the number of consecutive
periods of time under different conditions. For example, you might need to
calculate months of employment and unemployment, or days on and off a
medication. This paper describes how to use multiple arrays and index
variables to identify the beginnings and endings of spells, and how to
summarize the number, minimum, maximum, and average length of spells.
3:30 p.m.
4:15 p.m.
Using SAS® to Build Web Pages Linking Photographs
with Google Maps
Arthur Tabachneck, myQNA
William Klein, Retired
Yes, We Can... Save SAS® Formats
John Ladds, Statistics Canada
Paper 429-2012
Many of us at least occasionally take a picture with either a digital camera
or cell phone. And some of us, be it for work, a SAS user group, or for
personal use, end up posting some of our pictures on a Web page. JPG files
can contain a lot more information than just the pictures one sees,
including such data as when and where pictures were taken, titles, picture
heights and widths, and many of our camera’s settings. This paper includes
all of the Base SAS® code needed to create Web pages that show ones
pictures, in date taken order, with links that, when clicked, will cause
Google Earth to show you to where the pictures were taken.
3:45 p.m.
Beep, Beep, Beep, Back It Up! A Foolproof Approach to
Archiving with No Copying
Kristen Harrington, Rho, Inc.
Paper 046-2012
Have you been asked to revise a derivation and then several months later
asked to revert back to the previous code? Or when a project ends, were
you asked to remove it from the network? What if Archival Software is not
an option? This paper presents an “archiving” macro (%Archive()) which
takes the contents of a directory, including subdirectories, and creates a zip
file that contains all files and mirrors the parent’s directory structure. Like
magic, your code is saved and easily retrieved! Using an array of SAS®
functions, an X command, and WinZip, the %Archive() macro determines
the execution location and the subdirectories contents associated with that
location. With virtually no parameters, anyone can archive and look like a
pro while doing it.
4:00 p.m.
Working the System: Our Best SAS® Options
Patrick Thornton, SRI International
Iuliana Barbalau, Roche Molecular Systems
Paper 047-2012
This paper provides an overview of SAS system options and discusses the
best options. These are options that are beneficial, interesting, or both.
There are many ways to work the SAS system by changing the settings of
one or more of hundreds of system options. These settings can have
sweeping effects that influence DATA steps (REPLACE and MERGENOBY=),
the Log (MSGLEVEL=), data sets (VALIDVARNAME), listing output (NODATE,
NONUMBER, ORIENTATION=, and FORMDLIM=), and other destinations
(PDFSECURITY=). Option settings are invaluable for working with format
catalogs (FMTSEARCH=), and they are essential for using, developing, and
debugging macro programs (MPRINT, MLOGIC, MPRINT, SYMBOLGEN, and,
Paper 048-2012
If you share the results of your SAS programs with anyone, you likely use
SAS formats. Each time you run your program, you recreate the formats.
This format recreation takes time, it adds to the length of your log, the
formats do not change once you have created them and SAS issues
warnings that the formats already exists. Nonetheless, you still create them
over and over again. Well, did you know that you can easily create your
formats once, save them and re-use them again and again? If you are
feeling generous, you can even share them with others.
4:30 p.m.
Best Practices: Clean House to Avoid Hangovers
Mary Rosenbloom, Edwards Lifesciences, LLC
Kirk Lafler, Software Intelligence Corporation
Paper 049-2012
In a production environment, where dozens of programs are run in
sequence, often monthly or quarterly, and where logs can span thousands
of lines, it’s easy to overlook the small stuff. Maybe a data statement fails to
execute, but one already exists in the Temp library from a previous
program. Maybe a global macro assignment is missed or fails to execute,
but a global macro of the same name already exists from a previous
program. This can also happen with macros. The list goes on. This paper
offers some suggestions for housekeeping that can be performed at the
end of each SAS® program to minimize the chance of a hangover.
4:45 p.m.
Convert Your Old Plots and Charts to New SG Plots and
Charts: Here's How
Gabe Cano, Altarum Institute
Paper 083-2012
It is definitely in your best interest to move your old SAS/GRAPH® plots and
charts to the new SG graphics suite. What was once a timeless exercise in
producing quality graphs has now been replaced by a rich graphics suite
environment. The SG graphics suite enables you to customize plots and
charts with better context-driven graphics options. With a little information,
you can quickly get started building or rebuilding your graph plots and
charts. SAS® continues to grow its Base SAS® product into a business-level
application that can better serve analysts and business users alike. This
presentation shows two examples of how to move your old SAS/GRAPH
plots and charts to the new SG graphics suite.
5:00 p.m.
Analysis of Clickstream Data Using SAS®
Sumit Sukhwani, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
Satish Garla, Oklahoma State University
Paper 100-2012
Analyzing Web data has become a must-have for businesses. Significant
research has been done in studying clickstream data to understand the
navigation behavior of users after visiting a Web site. Analyzing clickstream
data is not easy for most companies because Web logs are stored in a form
that is not suited for analysis. Before any meaningful analysis can be done,
much effort is spent in transforming server logs to the right form so that
they can be analyzed. This is one of the reasons why companies often use
third-party services (such as Webtrends, Adobe, or Google Analytics) to
analyze their Web log data. This paper demonstrates applying SAS® macro
programming to prepare a SAS data set from raw Web logs and to generate
summary reports.
5:15 p.m.
The DOW Loop: A Smarter Approach to Your Existing
Fuad Foty, U.S. Census Bureau
Paper 052-2012
Following the frequent use of the DOW loop’s logic, it became apparent to
me that the DOW loop structure could be easily extended to a greater
percentage of existing SAS® code. Some SAS® code includes PROC SQL
statements performed on large data sets that can easily be replaced by a
DOW loop construct. Other SAS code includes PROC SUMMARY data sets
that can be simply aggregated and merged into a new SAS data set without
having to leave the DATA step. In addition to reading the code in a more
logical way, the process enables faster and more efficient performance. In
this paper, I examine existing SAS code examples and discuss how to
convert them to include this new and exciting DOW loop method.
Data Management — Northern Hemisphere A-2
2:00 p.m.
What's New in SAS® Data Management
Nancy Rausch, SAS
Michael Ames, SAS
Wilbram Hazejager, SAS
Paper 110-2012
The latest releases of SAS® Data Integration Studio and DataFlux® Data
Management Platform provide an integrated environment for managing
and transforming your data to meet new and increasingly complex data
management challenges. The enhancements help develop efficient
processes that can clean, standardize, transform, master, and manage your
data. Latest features include capabilities for building complex control
processes, additional in-database ELT transformation capabilities, big data
capabilities, enhanced features for monitoring data and processes, and new
features for unstructured data access, master data, and metadata
management. This paper provides an overview of the latest features of the
products and includes use cases and examples for leveraging their
combined capabilities.
3:00 p.m.
10,000 Leagues of Data... Divide and Conquer OLAP
Cubes: Best Practices for High Volumes of Data
Stephen Overton, Zencos Consulting
3:30 p.m.
Developing a Flexible ETL Process to Let SAS® Capture
Data Changes Efficiently in a Data Warehouse and Clean
Up the Mess
Stephen Overton, Zencos Consulting
Paper 112-2012
Data sources integrated into an Enterprise Data Warehouse can and most
likely will have different extraction frequencies as well as differing time
granularities. One efficient way to load a data warehouse is to detect
changes in data sources and only keep new data or data which has
changed. This paper presents a flexible change data capture process to
extract and load new data during any phase of loading a data warehouse.
The process can run dynamically at any time and requires no set schedule.
This paper will also demonstrate a data retention process using Base SAS®.
Both processes are centrally managed and operate independent of each
4:00 p.m.
Best Practices for Managing and Monitoring SAS® Data
Management Solutions
Gregory Nelson, ThotWave Technologies, LLC
(Invited) Paper 113-2012
SAS® and DataFlux® technologies combine to create a powerful platform for
data warehousing and master data management. Whether you are a
professional SAS administrator who is responsible for the care and feeding
of your SAS architecture, or you find yourself playing that role on nights
and weekends, this paper is a primer on SAS Data Management solutions
from the perspective of the administrator. Here, we will review some typical
implementations in terms of logical architecture so that you can see where
all of the moving parts are and provide some best practices around
monitoring system and job performance, managing metadata including
promotion and replication of content, setting up version control, managing
the job scheduler, and discuss various security topics.
5:00 p.m.
How Does SAS® In-Database Analytics Impact Data
Adrian Jones, SAS
Paper 114-2012
Over the last few years, business analysts have been able to realize the
benefits of SAS In-Database Analytics through both performance
improvements and value generation. With SAS In-Database, users interact
with the data changes along with the process to develop and deploy
modeling outputs. This not only has an impact on the business processes to
support analytical activity, but also on the underpinning storage and data
management processes. This paper takes a look back at the uptake of SAS
In-Database Analytics and the impact it has had on the data architecture
and data management processes required to support such activity.
Paper 431-2012
High volumes of data can be summarized most efficiently using OLAP
technology. As volumes of data approach the millions and even billions of
rows of data, loading an OLAP cube can become extremely challenging due
to system constraints. This paper presents a technique that uses SAS®
macro programming to divide and load data incrementally into an OLAP
cube. Using this technique ensures the cube will build successfully but also
provides users access to the cube while it is being loaded. This paper also
highlights OLAP programming techniques that allow you to streamline the
cube building process and minimize the impact of errors.
Data Mining and Text Analytics — Northern
Hemisphere A-3
2:00 p.m.
Developing a Predictive Model for Customer Trip
Purpose to Be Integrated into Enterprise Strategy and
Jonathan Levine, Marriott International
(Invited) Paper 126-2012
Marriott International needed a single accepted metric of leisure travel as a
component of total business that allowed for nuanced measures and the
analysis of the impact of specific marketing campaigns. The Marriott
Rewards Customer Knowledge team created a predictive model that
estimated the likelihood that a stay was for business. The results of this
model will be used both in enterprise-wide reporting visible at the C-level
as well as in targeted marketing campaigns. This paper will address some of
the modeling approaches used, as well as some of the challenges faced,
including specific issues related to building a model to be incorporated into
a production ETL. Software used included SAS/STAT®, SAS® Enterprise
Miner™, SAS/ACCESS® Interface to Netezza, and SAS® Scoring Accelerator
for Netezza.
3:00 p.m.
Use of Cutoff and SAS Code Nodes in SAS® Enterprise
Miner™ to Determine Appropriate Probability Cutoff
Point for Decision Making with Binary Target Models
Yogen Shah, FedEx Services
Paper 127-2012
This paper illustrates the effective use of the Cutoff and SAS Code nodes in
SAS® Enterprise Miner™ to change the default cutoff value of predicted
probability during decision making with binary target models. SAS®, by
default, uses a cutoff value of 0.5 to predict a binary outcome from
predicted probabilities (for example, the chance of a primary outcome is
the same as a secondary outcome). This is unacceptable because the
observed proportion of a primary outcome is usually never 50%. SAS®
Enterprise Miner™ provides the Cutoff node to adjust the probability cutoff
point based on a model’s ability to predict true positive, false positive, and
true negative. This paper introduces a technique to analyze probability
cutoff using SAS® Enterprise Miner and SAS® Enterprise Guide®.
3:30 p.m.
Constructing a Credit Risk Scorecard Using Predictive
Andres Gonzalez, Banco Colpatria
Alejandro Bahnsen, Banco Colpatria
Ana Nieto, Banco Colpatria
Darwin Amezquita, Banco Colpatria
(Invited) Paper 128-2012
Traditionally the clusters analysis has been used as a descriptive tool, in
which the algorithm is used to create clusters of observations. In this paper
we propose the use of cluster analysis as a predictive algorithm. We applied
this methodology by first determining to which cluster a prospect client
belongs, and then calculate a specific credit risk scorecard for each cluster.
We will show that this approach presents better results than using a single
scorecard for all the clients.
4:30 p.m.
An Experimental Comparison of Classification
Techniques for Imbalanced Credit Scoring Data Sets
Using SAS® Enterprise Miner™
Iain Brown, SAS UK
Paper 129-2012
In this paper, we set out to compare several techniques that can be used in
the analysis of imbalanced credit scoring data sets. In a credit scoring
context, imbalanced data sets frequently occur as the number of defaulting
loans in a portfolio is usually much lower than the number of observations
that do not default. As well as using traditional classification techniques,
this paper also explores the suitability of gradient boosting for loan default
prediction. Five real-world credit scoring data sets are used to build
classifiers and test their performance. The results from this empirical study
indicate that Gradient Boosting performs very well in a credit scoring
context and is able to cope comparatively well with pronounced class
imbalances in these data sets.
5:00 p.m.
Comparison of K-Means, Normal Mixtures and
Probabilistic-D Clustering for B2B Segmentation Using
Customers’ Perceptions
Satish Garla, Oklahoma State University
Gary Gaeth, University of Iowa
Goutam Chakraborty, Oklahoma State University
Paper 130-2012
Cluster Analysis is a popular technique used by businesses and analysts for
market segmentation. For segmentation, clustering is used to split
customers in a market into meaningful groups such that the customers
within a group are similar and customers between the groups are dissimilar.
Several clustering methods and numerous clustering algorithms are
available in existing software packages and new ones frequently appear in
the literature. These methods and algorithms vary depending on how the
similarity between observations is defined or on other assumptions about
shapes of clusters, distributions of variables, etc. This paper describes a
comparative study of three clustering methods (K-means, Normal Mixtures
and Probabilistic-D) for segmenting business-to-business (B2B) customers
using their perceptions.
5:30 p.m.
Predicting Electoral Outcomes with SAS® Sentiment
Analysis and SAS® Forecast Studio
Jenn Sykes, SAS
Paper 131-2012
With the wide proliferation of text-based data on the Internet, there are
more opportunities for organizations to validate the claims made in their
structured data. Here, I use a combination of SAS Sentiment Analysis and
SAS Forecast Studio to predict the outcomes of popular elections when
polling data is not readily available. I also use these tools to validate the
outcomes of elections and check for potential instances of fraudulent
election administration. I use examples from the real world of politics and
the popular television show, “American Idol.”
Financial Services — Northern Hemisphere A-1
3:30 p.m.
10:30 a.m.
Using PROC GAM to Forecast Claims Reserves in the
Runoff Triangles
Ling Huang, Fulcrum Analytics Inc.
Applying Analytics to High-Performance Customer
Profitability Models in Financial Services
Tony Adkins, SAS
Gary Cokins, SAS
Paper 138-2012
Where financial services companies have looked at customers in the past,
much of the literature focuses on the “apex” customers. These are the top
10–50 customers by value, whose importance to the business means that
they demand an extraordinary service, often at the expense of profitability.
Historically, it was difficult to build models of a scale that produce customer
profitability, so models tended to stop at segment level. We have tended to
rely on the traditional rather arbitrary groupings used within a business,
and this can disguise important trends. Bringing together analytics and
high performance in memory profitability models allow us to discover
hidden patterns in behaviors that cross arbitrary boundaries in the financial
services industry and refine our interpretation of intermittent risks.
2:00 p.m.
Building an Optimal Execution Plan for Liquidity
Management Using SAS®
Wei Chen, SAS
Liping Cai, SAS
Jimmy Skoglund, SAS
Paper 140-2012
Liquidity risk is a risk of not being able to generate enough funds to meet
the payment obligation. There has been a growing amount of literature on
liquidity assessment and planning following the recent financial crisis. So
far, not enough attention is given to the liquidity execution. At the time of a
liquidity crunch, there are often multiple funding sources available. These
funds are available at different sizes with various constraints in order to be
cashed at fair cost. Quicker funding can be achieved at a much higher
trading cost. This paper proposes a project plan model for liquidity
execution with optimal conversion strategy using SAS. It provides a
solution at the time of liquidity plan execution and leads to preconstructing a practical liquidity profile.
3:00 p.m.
Building WOE Binned LGD Scorecards using SAS®
Enterprise Miner™
Anthony van Berkel, Bank of Montreal
Naeem Siddiqi, SAS
Paper 142-2012
Runoff triangle means the two-way tabulation according to the warranty
start time and duration. Forecasting adequate claims and setting up
suitable reserves in the runoff triangle is an important part of an insurance
company. Traditionally, the claims reserves are estimated by linear
regression models such as chain ladder in practice. A more accurate and
flexible model can be built by examining claims counts and claims size
separately, and then combine the estimates to compute the total claims
reserves. This paper focuses on fitting generalized additive models (GAM)
with PROC GAM to predict claims counts and claims size separately, and
then calculated the total claims reserves in the runoff triangles. The final
model is validated on a test dataset to check how the accuracy.
4:00 p.m.
Global Risk Management: How SAS® Manages Financial
Risk According to Diverse Financial Regulations
Ting Xu, SAS
Hao Qiu, SAS
Shibin Liu, SAS
Paper 143-2012
Financial institutions need to measure risks according to local regulatory
authorities, such as Basel II/III, FSD, and so on. Distributed financial
institutes are facing the challenge of global compliance of diverse risk
regulations. This paper depicts a simulated scenario: An analysis
environment is set up with instruments, portfolio data, and market data in
different language for different branch. A set of methods and analyses is
defined according to Basel II, CBRC, and FSD respectively. After the projects
are run, capital is calculated for branches with corresponding regulation
and local market data. Stress testing is then applied to individual branch.
You learn how SAS risk solutions perfectly support the measurement of
quantitative risk based on multiple regulations and can be implemented for
global financial institutions.
5:00 p.m.
Becoming the Smartest Guys in the Room: An Analysis of
the Enron Emails Using an Integration of Text Analytics
and Case Management
John York, SAS
Doris Wong, SAS
Dan Zaratsian, SAS
Paper 141-2012
Paper 144-2012
The Credit Scoring add-on in SAS Enterprise Miner is widely used to build
binary target (good, bad) scorecards for probability of default. The process
involves grouping variables using weight of evidence, and then performing
logistic regression to produce predicted probabilities. Learn how to use the
same tools to build binned variable scorecards for Loss Given Default. We
explain the theoretical principles behind the method and use actual data to
demonstrate how we did it.
By integrating SAS® Enterprise Case Management with SAS® Text Analytics,
you as an investigator gain an analytical advantage. SAS Enterprise Case
Management expedites fraud investigations by providing an organized
environment for managing investigation workflows, documentation, and
case notes. By leveraging SAS Text Analytics, you can index and categorize
each document, further enhancing search capabilities, uncovering root
causes, and saving time and money during time-sensitive investigations
and audits. The Case Management repository is valuable in itself, not only
as an organizational repository, but also as an source of knowledge with
alert capabilities that can be investigated with analytics in its own right. The
integrated capability of utilizing SAS Text Analytics with SAS Enterprise
Case Management is illustrated using the Enron email corpus.
Hands-on Workshops — Southern Hemisphere I
10:30 a.m.
SAS® Enterprise Guide® 4.3: Finally a Programmer’s Tool
Marje Fecht, Prowerk Consulting LLC
Rupinder Dhillon, Dhillon Consulting Inc.
every time the corporate data are refreshed. In this workshop, you learn to
be the armchair quarterback and build pivot tables without leaving the
comfort of your SAS® environment. In this workshop, you learn the basics of
Excel pivot tables and, through a series of exercises, you learn how to
augment basic pivot tables first in Excel, and then using SAS. No prior
knowledge of Excel pivot tables is required.
(Invited) Paper 145-2012
Hands-on Workshops — Southern Hemisphere II
Have you been programming in SAS for a while and just aren’t sure how
SAS Enterprise Guide can help you? This presentation demonstrates how
SAS programmers can use SAS Enterprise Guide 4.3 as their primary
interface to SAS, while maintaining the flexibility of writing their own
customized code. We explore:
2:00 p.m.
Go Beyond the Wizard with Data-Driven Programming
Renato Villacorte, Fairbank, Maslin, Maullin, Metz & Associates
• navigating the views and menus
(Invited) Paper 148-2012
• using SAS Enterprise Guide to access existing programs and enhance
Programming techniques that take advantage of Data-Driven Programming
will be demonstrated for Novice and Intermediate Users of Base SAS®. Most
users already take advantage of Data-Driven Programming with wizards.
Wizards harvest information through an interface and then write and
execute programs based on those parameters. As programmers’ skills
evolve, they may want to edit the product of a wizard in order to confront a
variety of problems that a wizard could not anticipate. Going a step further,
programmers can author their own wizards that make their own work
easier. The workshop will include demonstrations in working with built-in
SAS® wizards, developing simple Data-Driven Programs, and the use of
parameter-gathering techniques using Enhanced Editor, simple macro
language, and ODS.
• exploiting the enhanced development environment, including syntax
completion and built-in function help
• using Code Analyzer, Report Builder, and Document Builder
• adding Project Parameters and dynamic parameters to generalize the
usability of programs and processes
• leveraging built-in capabilities available in SAS Enterprise Guide to
further enhance the information you deliver
Hands-on Workshops — Southern Hemisphere II
10:30 a.m.
Pharma and Health Care Providers — Oceanic 1
The SAS® Hash Object: It’s Time to .find() Your Way
Peter Eberhardt, Fernwood Consulting Group Inc.
2:00 p.m.
(Invited) Paper 147-2012
“This is the way I have always done it and it works fine for me.” Have you
heard yourself say this when someone suggests a new technique to help
solve a problem? Most of us have a set of tricks and techniques from which
we draw when starting a new project. Over time, we might overlook newer
techniques because our old toolkit works just fine. Sometimes, we actively
avoid new techniques because our initial foray leaves us daunted by the
steep learning curve to mastery. For me the SAS hash object fell into this
category. In this workshop, we start with the fundamentals of the setting up
the hash object and work through a variety of practical examples to help
you master this powerful technique.
Hands-on Workshops — Southern Hemisphere I
2:00 p.m.
The Armchair Quarterback: Writing SAS® Code for the
Perfect Pivot (Table, That Is)
Peter Eberhardt, Fernwood Consulting Group Inc.
Louanna Kong, SAS
(Invited) Paper 146-2012
“Can I have that in Excel?" This is a request that makes many of us shudder.
Now your boss has discovered Excel pivot tables. Unfortunately, he has not
discovered how to make them. So you get to extract the data, massage the
data, put the data into Excel, and then spend hours rebuilding pivot tables
Using Custom Data Standards in SAS® Clinical Data
Michael Kilhullen, SAS
Paper 167-2012
SAS Clinical Data Integration is a product offering from SAS® that enables
you to collect and centrally manage metadata about how clinical data is
transformed to published industry standards. However, many companies
already have internal standards that enable greater business process
efficiencies, or use standards that are dictated by an external source. This
paper discusses how a custom standard can be added to SAS Clinical Data
Integration and used in metadata management and data mapping features
to transform data to the custom standard.
3:00 p.m.
Your “Survival” Guide to Using Time-Dependent
Melissa Bagnell, Henry Jackson Foundation
Teresa Powell, Henry Jackson Foundation
Paper 168-2012
Survival analysis is a powerful tool with many strengths, like the ability to
handle variables that change over time. Including time-dependent
variables in survival analyses models, such as income, marital status,
location, or treatment, can more accurately assess the data. This paper will
give examples of the counting process syntax and programming
statements. These are the two methods to apply time-dependent variables
in PROC PHREG. Coding techniques will be discussed as well as the pros and
cons of both methods.
3:30 p.m.
Posters — Posters Area
Using the SAS® ODS Report Writing Interface to Create
Clinical Study Reports
Rui Duan, University of Miami
2:00 p.m.
Paper 169-2012
Summary tables and listings are the most common components in clinical
study reports. Different tables and listings in one study usually share a
similar layout. Clinical study reports are often converted to Rich Text Format
(RTF), and then distributed and viewed as Microsoft Word files. Different
methods have been developed to automate the creation of summary tables
and listings. This paper demonstrates a new approach to creating clinical
study reports using the SAS® ODS Report Writing Interface.
4:00 p.m.
Practical Application of SAS® Capabilities for Pharma
Goaling and Performance Review
Ramya Purushothaman, Cognizant Technology Solutions, Pvt.
Paper 170-2012
This paper discusses a Pharma application that uses SAS® to leverage
internal and purchased information such as Sales and Marketing data
including drug prescriptions, dollar and unit demand, target prescribers,
and key customer account profiles to set goals, measure sales performance
and identify trends across the geography. The capability of SAS to handle
huge volumes of data seamlessly provides an advantage over other
technologies. The reusability of SAS macros makes SAS solutions extensible
across various brands, sales teams, and geo levels for reporting. All of these
tasks are performed through familiar Base SAS® procedures, functions,
statements, and options. The paper explains how the business need is
addressed using SAS by accessing, cleansing, and transforming
4:30 p.m.
Applying Business Analytics to Optimize Clinical
Research Operations
David Handelsman, SAS
Paper 171-2012
SAS® is widely accepted as the gold standard in determining safety and
efficacy for clinical trials, and it provides the primary mechanism for
preparing data for these traditional clinical research analysis activities. Most
SAS users in the biopharmaceutical industries, however, are unaware of the
broad range of SAS analytics that are widely applied in other industries. This
paper discusses and describes how SAS’ business and advanced analytics
can be used to design better trials, forecast patient-based activities, and
optimize other operational processes. The application of business and
advanced analytics to clinical trial operations represents a new and
improved approach to reducing the cost and time associated with
managing clinical research projects, as well as expanding the roles of SAS
experts in the biopharmaceutical industries.
Programming the Provider Previews: Extreme Reporting
in SAS®
Christianna Williams, Independent Consultant
Louise Hadden, Abt Associates, Inc.
Paper 213-2012
Each month, we produce more than 15,000 data-driven reports (each report
being three pages) for nursing homes, previewing their five-star ratings on
various measures. These reports are produced entirely by SAS, including a
macro toggle for test or production mode and the collection of 15,000 PDF
documents into a single multi-gigabyte zip file. The elements of the
program include SAS macros, the DATA step, the REPORT procedure, and
the PDF statement in the SAS® Output Delivery System (ODS). Each PDF
document is named to easily upload into specific electronic mailboxes for
each nursing home facility.
2:00 p.m.
Put a Little Zip in Your SAS® Program
Louise Hadden, Abt Associates, Inc.
Christianna Williams, Independent Consultant
Paper 214-2012
SAS programmers are frequently called upon to perform repetitive
processes. To deal with repetitive processing SAS macros are indispensable.
If a process calls for using software outside of SAS, it might be hard to figure
out how to use SAS macros. This paper presents a solution to passing SAS
macro code through to an external software call. A bonus is the ability to
generate a listing of the resulting zip file and to output it to an external file
within the SAS program so that processing done in batch can be easily
checked. This example is run on a Microsoft Windows x64 server using
WinZip. However, the process can be used on other platforms and with
other software.
2:00 p.m.
Finding the Winning Combination: An Application of
Multivariate Testing from Digital Marketing
Robert Krutsick, True Action Network
Paper 206-2012
When designing a marketing campaign, marketers must identify the
appropriate mix of offer elements to optimize their desired measure of
campaign performance (such as response, conversion, sales, and profit).
This is not usually a trivial task since the number of offer elements making
up a typical marketing campaign can be quite large. The chosen mix of
offer elements included in a campaign is usually based on a combination of
business judgment and the results of experimental testing. In this paper, we
present an application of multivariate testing from the field of digital
marketing analytics. We demonstrate how to design a fractional factorial
test with JMP® and how to predict the optimal combination of offer
elements with the GLIMMIX procedure.
2:00 p.m.
2:00 p.m.
A SAS® Tip-of-the-Day Web Page on an Intranet
Bruce Gilsen, Federal Reserve Board
Using PHREG for Model Selection to Explore the Time
Taking Immigrants in the GB to Find First Employment
and Cross Validating Frailty Terms
JuYin Wong, University of Manchester
Paper 199-2012
For the past four years I have posted a SAS tip of the day on the Federal
Reserve Board's SAS Consulting Web site, which is part of the Board's
intranet site, FedWeb. In this paper, I will discuss design considerations for
the tips and display some tips. I also discuss and display the Web pages on
the SAS Consulting site that provide links to the tips.
2:00 p.m.
Calculating Multi-Rater Observation Agreement in
Health Care Research Using the SAS® Kappa Statistic
Abbas Tavakoli, University of South Carolina
Bo Cai, University of South Carolina
Rita Snyder, University of South Carolina
Nathan Huynh, University of South Carolina
Paper 201-2012
The processes are described for calculating multi-rater observation
agreement using the SAS® kappa statistic in a health care research study of
the medication administration process (MAP). Registered nurses modeled
the oral MAP a total of 27 times in a simulated laboratory environment.
Four individuals observed each of the 27 modeling sessions and recorded
the MAP functions and tasks observed for each session. Inter-rater reliability
(IRR) among the four observers was examined using the kappa statistic and
calculated using the SAS® FREQ, MEANS, and PRINT procedures. Results
from pairwise comparisons ranged from fair to good. This technique
expands the current functionality of the FREQ procedure to support kappa
statistical analysis for more than two raters and several categories.
Paper 216-2012
Instead of modeling (repeated) cross sectional or panel data when
comparing immigrants’ employment patterns, this study employs Cox
models to explore the length of time taking immigrants in the GB to find
their first employment to measure whether any transition-duration
penalties (i.e., the length of time for a transition to take place) experienced
by ethnic minority when compared to the majority groups. Frailty and
stratifying terms were tested to take account of unobserved individual and
geographic heterogeneities. Besides testing the default option of the frailty
term in PHREG, three other frailty models were also tested to validate the
significance test results of the frailty term.
2:00 p.m.
The Path to Developing Your Organization's SAS® Skills
Jonathan Boase, Humana
Donald Kros, Futrix
Paper 215-2012
As organizations try to leverage data assets and analytics as a means to
achieving competitive advantages, it becomes imperative to develop the
talent of the employees. This paper outlines the methodology that we
employ to collaborate with SAS® to provide our users with a SAS training
curriculum. This training path assumes little to no prior SAS experience and
leads users through a series of courses that will teach them the SAS skills
needed to reach that organizational goal.
2:00 p.m.
2:00 p.m.
MV_META: A SAS® Macro for Multivariate Meta-Analysis
Julie Gloudemans, University of South Florida
Corina Owens, Battelle
Jeffrey Kromrey, University of South Florida
Examples of Building Traceability in CDISC ADaM
Datasets for FDA Submission
Xiangchen Cui, Vertex Pharmaceuticals, Inc.
Hongyu Liu, Vertex Pharmaceuticals, Inc.
Tathabbai Pakalapati, Vertex Pharmaceuticals, Inc.
Meta-analysis of multiple outcomes and multiple treatments from a single
study require more sophisticated models than the typical meta-analytic
models. Three different approaches have been suggested to accommodate
dependent effect sizes: a multivariate multi-level approach (Kalaian &
Raudenbush, 1996), a robust variance estimation strategy (Hedges, Tipton,
& Johnson, 2010), and the traditional univariate random effects approach
(Hedges & Olkin, 1985). This paper presents a SAS macro that calculates
multivariate meta-analysis confidence intervals, mean effect sizes, and
estimated effect size variances for each outcome variable given a sample of
effect sizes and sample sizes. This paper includes a demonstration of the
macro, sample inputs and output, and an examination of the accuracy and
precision of the three approaches based on a simulation study.
Paper 205-2012
Paper 210-2012
Traceability in context of ADaM data sets means providing the method
followed to derive an analysis endpoint from source SDTM data. CDISC
ADaM IG 1.0 strongly recommends the incorporation of traceability feature
in ADaM data sets submitted to FDA. Traceability in derived data sets
increases confidence and provides transparency to agency reviewers which
might help in expediting the review and approval process. This paper
provides examples in applying the inherent traceability features available in
ADaM Basic Data Structures (BDS), adding SRCDOM, SRCVAR, and SRCSEQ
variables and with examples about adding Relation Criteria and Relation
Factor variables in ADaM data sets [2]. This paper tries to provide insight on
tradeoffs and limitations of traceability. The examples in this paper were
from FDA submissions.
2:00 p.m.
A Corporate SAS® Community of Support
Barbara Okerson, WellPoint
(Invited) Paper 198-2012
Many SAS users are not aware of an abundance of resources available to
them from a variety of sources. The available resources range from those
internal to their own organization to SAS itself. In order for these resources
to be utilized they need to be available to the users in an accessible way.
This paper shows how one large company with SAS users at many locations
throughout the United States has built a highly successful collaborative
community for SAS support. Modeled in the style of, the
online corporate SAS community includes discussion forums, surveys,
interactive training, places to upload code, tips, techniques, and links to
documentation and other relevant resources that help users get their jobs
2:00 p.m.
Wake Up Your Data with Graph'n'Go
Christopher Battiston, Hospital for Sick Children
Paper 217-2012
Graph'n'Go is a quick and easy way to visualize your data, from simple bar
charts to complex, multi-graph dashboards. With a lot of the functionality
being hard to find, this presentation aims to navigate the new user through
GnG to find the hidden gems. These will enable the newcomer not only to
produce graphs effectively, but will also teach them about SAS®
2:00 p.m.
“A Week in the Life”: A Visual Analysis of Internet Use by
School-Age Students
Simon King, Cary Academy
Aaron Daniels, Cary Academy
Jacob Warwick, Cary Academy
Paper 197-2012
This study took data of the Internet web hits for one week for the students
at Cary Academy, a grades 6–12 independent public school in Cary, North
Carolina. All students have their own school-issued tablet PC. Social
networks are blocked while students are in school. Student web hits were
monitored from 8 a.m. to Midnight for a school week. It was discovered that
student Internet use was up to twice as frequent outside of school, with the
use of social network sites increasing greatly for upper-school students,
with only a small increase for middle school students. All students showed a
significant use of “streaming” websites, a more recent Internet trend.
Conclusively, Internet use is not “out of control” in the classroom.
2:00 p.m.
Application of Time Series Clustering Using SAS®
Enterprise Miner™ for a Retail Chain
Karthik Nakkeeran, Oklahoma State University
Satish Garla, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
Paper 200-2012
Much of the data that are generated in the operational side of a business
have a built-in time dimension. One of the challenges of doing data mining
using such time-series data is the complexity of handling a large number of
time series. Time series clustering provides a way to reduce the complexity
by categorizing large number of time series into a smaller subset such that
series within each subset are relatively homogenous but series between
subsets are heterogeneous. SAS® has recently introduced new nodes for
finding similarities between the time series and to forecast their future
trajectories. In this paper we demonstrate clustering of store-level revenue
over time and how profiling of such clusters generate additional business
2:00 p.m.
How Test Length and Sample Size Have an Impact on the
Standard Errors for IRT True Score Equating: Integrating
SAS® and Other Software
Yi-Fang Wu, Iowa Testing Programs, University of Iowa
Paper 208-2012
The standard error of equating is a useful index to quantify the amount of
equating error. It is the standard deviation of equated scores over
replications of an equating procedure in samples from a population or
populations of examines. The current study estimates the SE of item
response theory true score equating in the Nonequivalent Groups with
Anchor Test design using simulations. Specifically, the test length of the
internal anchor and the sample size are of interests. Some specialized
programs, such as BILOG-MG 3.0 for item calibration, ST for IRT scale
transformations, and PIE for IRT true score equating, are incorporated to
accomplish the equatings. The purpose of the paper is to demonstrate such
a complicated and repetitive procedure through SAS.
2:00 p.m.
Easily Add Significance Testing to your Market Basket
Analysis in SAS® Enterprise Miner™
Michael Faron, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
Paper 204-2012
Market Basket Analysis is a popular data mining tool that can be used to
search through data to find patterns of co-occurrence among objects. It is
an algorithmic process that generates business rules and several metrics for
each business rule such as support, confidence and lift that help
researchers identify “interesting” patterns. Although useful, these popular
metrics do not incorporate traditional significance testing. This paper
describes how to easily add a well-known statistical significance test, the
Pearson’s Chi Squared statistic, to the existing output generated by SAS
Enterprise Miner’s Association Node. The addition of this significance test
enhances the ability of data analysts to make better decisions about which
business rules are likely to be more useful.
2:00 p.m.
Perils of Ignoring Social Media
Ping Koo, Singapore Management University
(Invited) Paper 212-2012
In 2010, we saw Social Media gaining influence over consumers while
businesses remain apprehensive of engaging conversations online.
Consumers have no qualms in making their voices heard on Social Media at
all. Moreover, Social Media has become an avenue for consumers to seek
more information before they make their purchase or patronize a service
provider. Such behavior is even more prevalent with the coming of
smartphones. Smartphones have developed a big group of “untethered”
consumers that together with the abovementioned behavior, has offered
“real-time” information to the communities they reside in and thus may
affect buying decisions by the hundreds. In this paper, we are going to
illustrate with examples of how businesses have responded to the
challenges that social media brought to them.
2:00 p.m.
Investigating Host Plant Resistance to Aphid Feeding
through SAS® Text Miner
Ning Song, Oklahoma State University
Jiawen Liu, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
James Anstead, Pennsylvania State University
Paper 209-2012
The processes of host plant resistance to insect feeding and pathogen
attack are involved with several complicated plant defense pathways
comprising numerous regulations of pathogen-related gene expressions.
The aim of this study is to examine the ethylene signaling defense pathway
of melon plant. Here, we present a novel way of applying text mining in
plant resistance research literature review. SAS Text Miner was employed to
analyze current literature emphasis with the purpose of identifying
interesting and important research trends in the field of host plant resistant
to insect attacking. It was shown that ethylene, jasmonic acid, salicylic acid,
calcium signaling pathways are major emphasis in the plant-pathogen
interaction field. Additionally, SAS® Enterprise Guide® was used to analyze
gene expression changes in ethylene signaling pathway.
2:00 p.m.
Creating Pharmacokinetic Graphs Using SAS/GRAPH®
Katrina Canonizado, Celerion
Matthew Murphy, Celerion
Paper 203-2012
Graphs are visual representations of data. In a clinical trial setting, figures
show the general trends and relationships of variables collected during the
conduct of a study. In the pharmacokinetic world, graphs play an important
role in showing the drugs concentration profiles. A line graph is a typical
way to present a drug’s concentration. However, depending on the data
available and the analysis required, different visual presentations, such as
scatter plots, spaghetti plots, and many more, are needed to fully
communicate the information at hand. These graphs can be created using
SAS/GRAPH®. This paper demonstrates some available SAS/GRAPH
procedures, options, and the Annotate facility for producing effective
pharmacokinetic graphs.
2:00 p.m.
One at a Time; Producing Patient Profiles and Narratives
Joseph Hantsch, PharmaNet/i3
Janet Stuelpner, SAS
(Invited) Paper 211-2012
Patient profiles can take many forms depending on the purpose for which
they are going to be used. For data cleansing, it can be a data dump for
each patient so that any data anomalies can be discovered. For medical
review, the narrative type of profile would best. All of this can be done with
Base SAS® and macros to create the listings, formatted profiles, and
narratives. An alternative is with a data visualization tool, JMP® Clinical.
Patient profiles are customizable and can display data from any
combination of the core safety CDISC domains. A configurable patient
narrative can be created for each subject who experienced a serious
adverse event during the clinical trial.
2:00 p.m.
Getting Started with ODS: Generating Formatted
Reports Using the ExcelXP Tagset
Allan Rosario, Marriott International
Jennifer Mefford, Marriott International
Paper 207-2012
In the business world, reporting is a key component in presenting data to
the user. Using the power of the SAS® ODS ExcelXP tagset destination to
customize report structure and format is one method of report creation.
This method is particularly well-suited to automating the production of
multiple Excel workbooks that are nicely laid out for users. This paper shows
a simple approach to getting started with writing ODS using the ExcelXP
tagset. It demonstrates how to use the ODS style options to generate
formatted reports in Excel directly from SAS®, and demonstrates how to
easily add iterative DO loops and macro variables to automatically generate
multiple formatted reports.
2:00 p.m.
Creating a Report in the SAS® Information Delivery
Portal Using SAS® Information Maps
Jenine Milum, Wells Fargo & Co.
(Invited) Paper 202-2012
This paper guides a SAS® BI developer through the steps necessary to
combine SAS data sets using SAS Information Maps and create a report
which becomes available in the SAS Information Delivery Portal. The result
is a professional report viewable by business users within their browsers.
Using the tools below to create a report available in the Information
Delivery Portal frees business users from concerning themselves with data
construction, security, information updates, and collection requirements.
The business user can focus on Analysis and other tasks without needing to
be a SAS developer. SAS® 9.2 is used with these SAS products:
• SAS® Management Console
• SAS® Information Map Studio
• SAS® Web Report Studio
• SAS® Information Delivery Portal
Programming: Beyond the Basics — Asia 5
10:30 a.m.
What to Do with a Regular Expression
Scott Davis, Experis
Paper 219-2012
As many know, SAS® has provided support for regular expressions for some
time now. There are numerous papers that expose the basic concepts as
well as some more advanced implementations of regular expressions. The
intent of this paper is to narrow the gap between the very beginning and
the advanced. In the past you might have solved a programming problem
with a combination of SUBSTR/SCAN and other functions. Now a regular
expression may be used to greatly reduce the amount of code needed to
accomplish the same task. Think of this paper as a recipe or guide book that
can be referenced for some real-life examples that will hopefully get you
thinking about ways to create your own regular expressions.
11:00 a.m.
Advanced XML Processing with SAS® 9.3
Thomas Cox, SAS
used to explore how things “really work,” make code more concise,
implement en masse data movement and, oftentimes, achieve truly
incredible gains in execution efficiency. In this paper, APP techniques are
explored in a systematic manner. Welcome to the APP world! You are in for
a few pleasant surprises.
Paper 220-2012
XML has expanded far beyond the scope originally envisioned by its
creators, and this has resulted in the addition of companion standards such
as Namespaces in XML and XML Schema. This paper describes how SAS has
advanced our XML technology in SAS® 9.3 to more fully support these
standards. It also examines some of the challenges you might encounter
when processing complex XML and describes some best practices to help
overcome the challenges.
3:30 p.m.
Parallel Computing in SAS®: Genetic Algorithms
Alejandro Bahnsen, Banco Colpatria
Darwin Amezquita, Banco Colpatria
Andres Gonzalez, Banco Colpatria
2:00 p.m.
Paper 224-2012
Interesting Technical Mini-Bytes of Base SAS®—From
DATA Steps to Macros
Airaha Manickam, Cognizant Technology Solutions, Pvt. Ltd.
Genetic Algorithms is a very powerful optimization technique that can be
used in a wide variety of problems. But unfortunately the performance of
this methodology relies heavily on computer power. We used Genetic
Algorithms to select the architecture of a Multi-Layer Perceptron Neural
Network and even though results indicated that it improves the predictive
power of this type of models applied to credit risk scorecards, it is also very
time consuming and computationally expensive. Because of this, we
implemented a version of Parallel Genetic Algorithms in SAS using PROC
CONNECT. Results show that parallel computing can drastically reduce the
total execution time of the genetic algorithm.
Paper 222-2012
Over the last several decades, SAS has improved and added thousands of
features to Base SAS®. It is almost impossible for someone to know all of the
tricks and tips of Base SAS. This paper highlights some useful tips and
advanced tricks of Base SAS that I have encountered during my experience
working with SAS. These technical mini-bytes are divided into two sections
—DATA step mini-bytes and macro mini-bytes. In this paper, I present
interesting examples involving common and advanced DATA step
executions such as CALL SET, dynamically accessing SAS data sets, and PERL
pattern matching. Similarly, simple to advanced macro tips including CALL
EXECUTE and QUOTE functions in macros are discussed.
4:00 p.m.
Sudoku-Solving System by SAS®
Setsuo Suoh, The University of Hyogo
(Invited) Paper 225-2012
Programming: Beyond the Basics — Americas
Seminar Room
2:00 p.m.
Tales of SAS® 9.3: A Collection of Uses
David Shamlin, SAS
Paper 218-2012
In this presentation, hosted by David Shamlin, expert SAS presenters
discuss new features in SAS 9.3. An expert user then uses each new feature
and describes his or her experience with it. The attendee should leave this
presentation with a working knowledge of each of these new features.
Programming: Beyond the Basics — Asia 5
2:30 p.m.
Straight from Memory: ADDR, PEEK, POKE as SAS
Programming Tools
Paul Dorfman, Paul Dorfman Consulting
William Viergever, Viergever & Associates
(Invited) Paper 223-2012
The ADDR, PEEK, and PEEKC functions, as well as the CALL POKE routine,
and their 64-bit "LONG" counterparts ("APP functions") are the SAS tools
designed to communicate information directly between DATA step
expressions and physical memory. It turns out that despite their relative
obscurity, APP functions are rather simple and useful tools. They can be
We’ve developed the Sudoku-Solving System by SAS. The SAS data set is
supposed to be the most inconvenient data set to attack Sudoku puzzles
because of its structure. Our system has four crucial factors: (1) how to
depict the values of 81 boxes in a SAS data set environment; (2) how to
attack Sudoku puzzles efficiently and smartly without using brute force; (3)
the recursive technique employed for tree searching during the attacking
process, using the %INCLUDE statement; (4) an option for recording all of
the attacking process or history of a tree search. It consists of four SAS
programs, one of which has about 40 SAS macro definitions, and succeeded
in solving the hardest Sudoku puzzles available on the Internet in about
three minutes.
5:00 p.m.
The Good, The Bad, and The Ugly
Toby Dunn, Dunn Consulting
Kirk Lafler, Software Intelligence Corporation
(Invited) Paper 226-2012
The SAS® System has all the tools users need to read data from a variety of
external sources. This has been, perhaps, one of the most important and
powerful features since its introduction in the mid-1970s. This paper will
provide insights into the INFILE statement, the various styles of INPUT
statements, and provide numerous examples of how data can be read into
SAS with the DATA step. We will show how to use the features of the INFILE
statement along with the inherent functionality of the DATA step to read
not only well formed external files but also the extreme cases such as
reading in all files in a directory and how to read data that is scattered over
multiple lines.
Programming: Foundations and Fundamentals —
Asia 4
10:30 a.m.
A Survey of Some of the Most Useful SAS® Functions
Ronald Cody, Private Consultant
(Invited) Paper 241-2012
Most SAS programmers know a few functions, but in the latest release of
SAS, there are some new and wonderful functions that will change the way
you program. This presentation is a survey of some of the most useful
functions and CALL routines. Do you know about the MISSING function or
about a CALL routine that sorts values within an observation? How about
the YRDIF function that computes ages, or a function that counts
characters? Or my favorite, a function that can extract digits from a
character string. I hope that you will leave this 50-minute tutorial a much
better SAS programmer.
prior dates are negative numbers, those after have positive values. Despite
SAS dates being part of the initial learning curve, there are a number of
factors concerning dates that are frequently less than obvious to users,
even experienced users. In this presentation, we focus on displaying/
outputting SAS dates (formats), reading dates (informats), importing/
exporting dates, calculating intervals and differences (functions), and
extracting or combining portions of dates (more functions).
4:00 p.m.
Using the New Features in PROC FORMAT
Rick Langston, SAS
Paper 245-2012
This paper describes several examples using functions as labels within
PROC FORMAT definitions. Also described is the new feature allowing for
Perl regular expressions for informatting data, as well as other new features
in PROC FORMAT for SAS® 9.3.
11:30 a.m.
5:00 p.m.
PROC REPORT Basics: Getting Started with the Primary
Art Carpenter, CA Occidental Consultants
Simplifying Effective Data Transformation via PROC
Arthur Li, City of Hope/University of Southern California
(Invited) Paper 242-2012
(Invited) Paper 246-2012
The presentation of data is an essential part of virtually every study and
there are a number of tools within SAS® that allow the user to create a large
variety of charts, reports, and data summaries. PROC REPORT is a
particularly powerful and valuable procedure that can be used in this
process. It can be used to both summarize and display data, and is highly
customizable and highly flexible. In this introduction to PROC REPORT, you
will learn to use the PROC REPORT statement and a few of its key options.
Several supporting statements, including COLUMN, DEFINE, BREAK, and
RBREAK, and their primary options will also be covered.
You can store data with repeated measures for each subject, either with
repeated measures in columns (one observation per subject) or with
repeated measures in rows (multiple observations per subject).
Transforming data between formats is a common task because different
statistical procedures require different data shapes. Experienced
programmers often use ARRAY processing to reshape the data, which can
be challenging for novice SAS® users. To avoid using complex
programming techniques, you can also use the TRANSPOSE procedure to
accomplish similar types of tasks. In this talk, PROC TRANSPOSE, along with
its many options, will be presented through various simple and easy-tofollow examples.
2:00 p.m.
My Friend, the SAS® Format
Andrew Karp, Sierra Information Services
(Invited) Paper 243-2012
Formats play many important roles in SAS® and offer powerful ways to
manage and present your data. This step-by-step tutorial introduces you to
the core concepts and capabilities of the SAS format facility. It shows you
how to use SAS formats to control how data values are displayed in your
output, as well as how to use PROC FORMAT to create customized formats
for your data. You see how formats are used to group and display data in
core Base SAS® procedures, and you see an overview of the new
MULTILABEL format facility. This presentation is appropriate for newer users
of SAS programming tools who want to get the most from what this
powerful tool can offer them.
3:00 p.m.
SAS® Dates: Facts, Formats, and Functions
Debbie Buck, PharmaNet/i3
(Invited) Paper 244-2012
Among the first features of SAS that users learn is that SAS dates (and
times) have unique characteristics. A SAS date isn’t a “standard” numeric or
character variable – when displayed it can look like character data but is
stored as a number. The date of January 1, 1960, has a value of zero (0) –
Reporting and Information Visualization —
Southern Hemisphere IV
2:00 p.m.
At the Crossroads: How to Decide on Your Graphics Path
Mike Kalt, SAS
Cynthia Zender, SAS
Paper 261-2012
Have you heard about ODS Graphics or ODS Statistical Graphs and
wondered what they mean to you? Do you have legacy SAS/GRAPH®
programs and wonder whether there’s any benefit going down the ODS
Graphics path? Are you at the graph crossroads and uncertain which way to
go? With the ODS Graphics capability as part of Base SAS® in SAS® 9.3, many
users find themselves at the crossroads, trying to decide what path to
follow—the traditional SAS/GRAPH path or the new ODS Graphics path.
This presentation focuses on helping you make an informed decision.
Although some concrete examples are shown, this presentation is aimed at
the SAS programmer or SAS® Enterprise Guide® user who wants to know
more before they set off down the graphics highway.
3:00 p.m.
Using SAS® GTL to Visualize Your Data When There Is
Too Much of It to Visualize
Perry Watts, Stakana Analytics
Nate Derby, Stakana Analytics
(Invited) Paper 262-2012
Developing a good graph with ODS statistical graphics becomes a
challenge when input data maps to crowded displays with overlapping
points or lines. Such is the case with the Framingham Heart Study of 5,209
subjects captured in the sashelp.heart data set and a series of 100 booking
curves for the airline industry. In addition, interleaving series plots can be
difficult to interpret, and patterns can be missed when lattice plot panels
are charted out-of-order. In the paper, transparency, layering, data point
rounding, median calculation, and color coding are evaluated for their
effectiveness to add visual clarity to graphics output. Graph Template
Language (GTL) statements and layouts referenced in the paper include
4:00 p.m.
Faking Esri ArcGIS Maps in SAS®
Anastasiya Osborne, Farm Service Agency, USDA
Paper 263-2012
This paper describes another successful project of automating manual tasks
at the Farm Service Agency (FSA), USDA. After an urgent request, we wrote
new SAS code with the GPROJECT procedure, the GMAP procedure, and
heavy use of annotation to map widely used state revenue guarantees and
benchmark yields for twenty-two crops under the Congressionally
mandated Average Crop Revenue Election (ACRE) program. Previously,
such maps were created in Esri ArcGIS. The SAS solution enhanced the
quality of the map. It showed state revenues and yields in a compact but
readable way, drastically improved presentation of data in Northeast states,
and eliminated the repetitive task of making a PDF file out of twenty-two
separate maps.
4:30 p.m.
Quick and Dirty Microsoft Excel Workbooks without
Dynamic Data Exchange or the SAS® Output Delivery
Andrea Wainwright-Zimmerman, Capital One
Paper 264-2012
There is a simple trick using the X command in SAS® that enables you to
write your SAS data to an already formatted Microsoft Excel workbook with
graphs and pivot tables that are already built. This paper describes how to
accomplish this task as well as how to manage the limitations of this
5:00 p.m.
Making Your SAS® Data JMP® Through Hoops
Mira Shapiro, Analytic Designers LLC
Paper 265-2012
Longtime SAS users can benefit by adding JMP to their repertoire. JMP
provides an easy-to-use and robust environment for data exploration,
graphics, and analytics without the need for programming expertise. This
paper provides an introduction to JMP® 9 with an emphasis on features that
SAS users will find useful. During this presentation, users learn how to read
their SAS data, import Excel spreadsheets, transform their data, explore
distributions, create reports and create sophisticated graphics all in the JMP
environment. Users are introduced to the tools within the JMP® 9
environment that provide a pathway to quickly learn how to use the
product and some of its unique features.
5:30 p.m.
Visualizing Spatial Data Using SAS® and Google Static
Jizhou Fu, NORC at the University of Chicago
Yanwei Zhang, CNA
Paper 266-2012
We present a new tool that enables SAS users to overlay various spatial
patterns on Google Static Maps in a straightforward manner. The tool relies
on the graphical functionality from the DATA Step Graphical Interface, and
it is structured in a way that a variety of graphical forms or spatial
information from different data sources can be combined effectively. We
give an extensive discussion of the design of the tool and related
background information, and provide detailed guidance on its use. Also,
the usefulness and the flexibility of this tool are demonstrated through
separate applications to survey field listing maps and crime distribution
Retail — Asia 1
10:30 a.m.
Really? Don’t Trust Your Gut with Assortment Planning
Ann Ferguson, SAS
Scott Sanders, Sears Holdings
Wesley Stewart, Family Dollar
(Invited) Paper 422-2012
Assortment-planning processes vary greatly across retailers and product
segments. What we know from experience is that they rely too much on
human judgment and not enough on solid hard data. Retailers today need
the ability to predict how customers will react to a change in the
assortment. This session will focus on what have we learned and how did
we overcome obstacles. As retailers, we are moving away from “one size fits
all” assortments. For some, analytics is playing a bigger role; for others,
business processes are changing on a regular basis. Fashion vs. Basics,
What’s working AND: How are we achieving optimal planning throughout
all phases of the merchandising process?
11:30 a.m.
Understanding impact of social media on online retail
Alexander Soria, Zappos
(Invited) Paper 432-2012
Given the convergence of social media and mobile channels, consumers are
increasingly armed with product and price information – all at the click of a
mouse or the swipe of a SmartPhone screen. In order to succeed in this
consumer-empowered environment, retailers must understand how online
behavior translates into web/store traffic and converted sales.. Zappos, a
leading Nevada-based online retailer has differentiated itself by connecting
with its customers, regardless of channel: phone, web, social media, or
mobile. In this session, you will hear how Zappos uses SAS Social Media
Analytics and other SAS software to identify relationships between social
behavior and business metrics that result in increased sales and unmatched
customer satisfaction and loyalty.
12:30 p.m.
Retail Solutions Update
Saurabh Gupta, SAS
Deva Kumar, SAS
Paper 288-2012
The goal of this presentation is to provide user groups with an update on
retail solution releases in the past year and the roadmap for moving
2:00 p.m.
Improving Retail Decisions with Customer Analytics:
Leveraging Actionable Customer Insights to Build Sales
and Profits
Wanda Shive, SAS
Dwight Mouton, SAS
Paper 286-2012
Customer-centric decision making is a key differentiator for retailers.
Collecting customer data is a common practice. Major challenges include
making customer offers more personal and delivering actionable customer
insights to merchants at the point of decision for assortment, pricing, and
promotions. Hear how retailers are increasing sales and profitability by
using optimization to improve redemption rates of customer-specific offers
and adding the customer dimension to key merchandising decisions.
3:00 p.m.
SAS® Markdown Optimization for Retail Round Table
Carrie Plaskas, Macy's
(Invited) Paper 420-2012
This session is designed to be a general discussion on SAS Markdown
Optimization. We provide an opportunity to ask questions and learn how
your peers are gaining the most value from this SAS® solution. Key topics
• How to extract the most value from SAS Markdown Optimization while
still supporting your merchandising strategies (product flow, inventory
management, store execution, etc.)
• Techniques used to improve price acceptance
• Metrics leveraged to measure success
4:00 p.m.
SAS® Integrated Merchandise Planning Round Table
Amy Clouse, Dick's Sporting Goods, Inc.
(Invited) Paper 419-2012
This session is designed to be a general discussion on the SAS Integrated
Merchandise Planning Solution. We will provide an opportunity to ask
questions and learn how your peers are gaining the most value from this
SAS® solution. Key topics will include:
• Assortment Planning best practices and efficiencies
• Reporting challenges and alternative solutions
SAS® IT Management — Gaylord Palms Resort,
Sun Ballroom
10:30 a.m.
How Analytics Can Help Turn IT Into True Business
Results Drivers
Scott Vaughn, Tech Web
Hung LeHong, Gartner
Pauline Nist, Intel
Gary King, Chicos
(Invited) Paper 386-2012
IT is under extreme pressure to deliver business value. Forward-thinking
executives and corporate boards are looking to their IT departments for
technology-based systems and processes that deliver true competitive
differentiation, speed the introduction of new products, help identify new
markets and more. This two-part session, comprised of a keynote address
by Hung LeHong from Gartner followed by a panel discussion, explores
how business analytics is driving IT’s increasingly strategic role.
1:00 p.m.
Analytic Infrastructure Design Considerations
Bryan Harris, Visti
Jessica Dunn, Bank of America
(Invited) Paper 387-2012
Did you know that half of productivity gains realized across all industries
can be attributed to IT? Going forward, SAS expects analytics to
complement IT innovation in driving additional productivity gains. In this
session, we'll make sense of the buzz around cloud, big data, highperformance computing and approachable analytics, and share how you
can design the right infrastructure to support a range of analytic disciplines
that boost productivity and confer competitive advantage.
2:00 p.m.
Information Management Strategy
Gavin Day, DataFlux Corporation
Scot Campbell, Pinnacle Entertainment
(Invited) Paper 388-2012
Smart organizations are now turning to a variety of technologies to manage
their data; in addition to traditional ETL technologies, data quality, MDM
and data governance are being harnessed to optimize data for operational
and analytical uses. In this session, we'll discuss key ways to move beyond
the traditional data management approach – reactive and silo-based – to a
managed, predictive approach that values information as a strategic asset
3:00 p.m.
3:00 p.m.
Meet the Speakers Networking Session
Keith Collins, SAS
Scot Campbell, Pinnacle Entertainment
Gary King, Chicos
Hung LeHong, Gartner
Pauline Nist, Intel
Scott Vaughn, Tech Web
SAS® Workshop: SAS® Enterprise Guide® 5.1
Eric Rossland, SAS
Paper 401-2012
This workshop provides hands-on experience using SAS Enterprise Guide.
Workshop participants will:
• access different types of data
• analyze data using the Data Explorer
• create reports and analyses
This is your opportunity to connect with the presenters from today’s IT
sessions and get their thoughts on your particular challenge. It’s also a
great time to network with SAS IT executives and other attendees
4:00 p.m.
SAS® Workshop Series — Asia 2
SAS® Workshop: SAS® Data Integration Advanced
Kari Richardson, SAS
10:30 a.m.
SAS® Workshop: SAS® Platform Administration
Christine Vitron, SAS
Paper 398-2012
This workshop provides hands-on experience using SAS® Management
Console to administer the platform for SAS® Business Analytics. Workshop
participants will:
• back up the metadata
• register a user in the metadata
• manage access to application features with roles
11:30 a.m.
SAS® Workshop: SAS® Add-In for Microsoft Office 5.1
Eric Rossland, SAS
Paper 399-2012
This workshop provides hands-on experience using the SAS Add-In for
Microsoft Office. Workshop participants will:
• access and analyze data
• create reports
• use the SAS add-in Quick Start Tools
2:00 p.m.
SAS® Workshop: SAS® Data Integration Basics
Kari Richardson, SAS
Paper 402-1012
This workshop provides hands-on experience using SAS® Data Integration
Studio to take advantage of the Loop transformations. Workshop
participants will:
• define and load a control table
• parameterize an existing job
• create an iterative job using the control table and parameterized job
5:00 p.m.
SAS® Workshop: Creating SAS® Stored Processes
Eric Rossland, SAS
Paper 403-2012
This workshop provides hands-on experience creating SAS Stored
Processes. Workshop participants will:
• use SAS® Enterprise Guide® to access and analyze data
• create stored processes which can be shared across the organization
• access the new stored process from the SAS® Add-In for Microsoft Office
Statistics and Data Analysis — Americas Seminar
10:30 a.m.
Handling Missing Data by Maximum Likelihood
Paul Allison, University of Pennsylvania
Paper 400-2012
(Invited) Paper 312-2012
This workshop provides hands-on experience using SAS® Data Integration
Studio to construct tables for a data warehouse. Workshop participants will:
Multiple imputation is rapidly becoming a popular method for handling
missing data, especially with such easy-to-use software like PROC MI. In this
talk, however, I argue that maximum likelihood is usually better than
multiple imputation for several important reasons. I then demonstrate how
maximum likelihood for missing data can readily be implemented with the
following SAS procedures: MI, MIXED, GLIMMIX, and CALIS.
• define and access source data
• define and load target data
• work with basic data cleansing
Statistics and Data Analysis — Northern
Hemisphere E-1
variable; and integration of the dummy coded variables, omitting a chosen
reference group, into PROC MIXED. Employing this approach expands the
use of PROC MIXED.
2:00 p.m.
Look Out: After SAS/STAT® 9.3 Comes SAS/STAT 12.1!
Maura Stokes, SAS
Fang Chen, SAS
Yang Yuan, SAS
Weijie Cai, SAS
Paper 313-2012
Heralded by a new release-numbering scheme, SAS/STAT 12.1 comes
loaded with new statistical capabilities. New development areas include
model selection for quantile regression, quantile regression for censored
data, and multivariate adaptive regression splines. Epidemiologists will like
the STDRATE procedure for computing direct and indirect standardized
rates and risks for study populations. The FMM procedure becomes
production and includes new features such as additional distributions.
Other notable enhancements include modeling missing covariates with the
MCMC procedure and fitting Bayesian frailty models with PROC PHREG. This
paper reviews highlights from earlier releases and describes highlights of
SAS/STAT 12.1, slated for release during 2012.
Statistics and Data Analysis — Northern
Hemisphere E-2
2:00 p.m.
Statistics and Data Analysis — Northern
Hemisphere E-1
3:00 p.m.
Propensity Score Analysis and Assessment of Propensity
Score Approaches Using SAS® Procedures
Rheta Lanehart, University of South Florida
Patricia Rodriguez de Gil, University of South Florida
Eun Kim, University of South Florida
Aarti Bellara, University of South Florida
Jeffrey Kromrey, University of South Florida
Reginald Lee, University of South Florida
Paper 314-2012
Propensity score analysis is frequently used to reduce the potential bias in
the estimated effects from observational studies. The appropriate
implementation of propensity score adjustments is a multi-step process
that presents many alternatives for researchers in terms of estimation and
conditioning methods. Furthermore, evaluation of the sample data after
conditioning on the propensity score informs researchers about threats to
the validity of the score adjustments from such an analysis. This paper
describes the steps required for a propensity score analysis and presents
SAS® code that can be used to implement each step.
Knowledge (of Your Missing Data) Is Power: Handling
Missing Values in Your SAS Data Set
Theresa Schwartz, NY Psychiatric Institute/Columbia University
Rachel Zeig-Owens, Montefiore Medical Center/FDNY
3:30 p.m.
Before you conduct any statistical tests, it is important to check for missing
values and evaluate how they may influence your study conclusions. This
paper presents an overview of considerations that need to be made when
you are confronted with missing data. The paper describes how to
efficiently check for missing values, as well as investigates how SAS handles
missing values and what can be done to correct for these missing values in
your analysis.
Paper 315-2012
(Invited) Paper 319-2012
3:00 p.m.
Using SAS® PROC MIXED to Fit Health Policy-Based
Hierarchical Models
Lori Miller, UC Davis Medical Center
Fred Wilds, Excellence in Travel Inc.
Paper 320-2012
SAS® procedure PROC MIXED is a flexible program for fitting complex
hierarchical linear models and calculating corresponding statistics.
Documentation for PROC MIXED, however, remains complex and the
defaults are often not appropriate. Using PROC MIXED does not preclude
the need for substantial data processing to prepare for modeling, data
analysis, and circumventing conversion issues due to the model including
36 public school groups and three or more student race/ethnicity and
socioeconomic status categorical variables. This paper demonstrates: the
process of aptly structuring a custom data set without use of array
applications; creation of dummy coded variables for each categorical
Effect Modification, Confounding,Hazard Ratio,
Distribution Analysis, and Probability of Non-normal
Data for Head Neck Cancer
Interaction methods for effect modification and confounding with the O
and Oc statistics that are asymptotic chi-square and a PROC IML algorithm
with PROC MIXED (SAS) Agravat (2011) combined with survival and
probability analysis for head neck cancer are demonstrated. In support of
these new interaction analysis methods are C stat, and power. A new
hazard logit for survival statistics for head neck cancer due to nonsmoking
by race including distribution analysis, hazard ratios, and calculations of
probability is demonstrated. Statistics based on probability, independence,
and algorithms are important when data are non-normal, linearity is not
present, homogeneity assumption for standard error is not met, and when
no time point is given. A new method for Z scores and risks based on logits
is introduced.
Statistics and Data Analysis — Northern
Hemisphere E-2
3:30 p.m.
Beyond Binary Outcomes: PROC LOGISTIC to Model
Ordinal and Nominal Dependent Variables
Eric Elkin, ICON Clinical Research
Paper 427-2012
The most familiar reason to use PROC LOGISTIC is to model binary (yes/no,
1/0) categorical outcome variables. However, PROC LOGISTIC can handle
the case where the dependent variable has more than two categories.
PROC LOGISTIC uses a cumulative logit function if it detects more than two
levels of the dependent variable, which is appropriate for ordinal (ordered)
dependent variables with 3 or more levels. A generalized logit function for
the LINK= option is available to analyze nominal (unordered) categorical
variables with 3+ levels (i.e., multinomial logistic regression). Detailed
examples will be given, emphasizing procedure syntax, data structure,
interpretation of statistical output, and ODS output data sets.
4:00 p.m.
A Simple Way to Program Power Calculations
Robert Lew, MAVERIC, VA Cooperative Studies Program, Boston
V.A. Healthcare System
Hongsheng Wu, MAVERIC, VA Cooperative Studies Program,
Boston V.A. Healthcare System
Paper 322-2012
We propose a simulation of large sets of statistical power calculations and
the selection of those calculations with appropriate power from a long list
of study designs. Typical commercial programs complete all but one
parameter and solve for the remaining parameter. We avoid solving
equations and, thereby, obtain power for atypical designs. For simplicity,
we compute the power for the test, comparing two proportions without
assuming either an approximate normality or a common variance. We also
extend the log-rank test power calculation to account for various patterns
of on-study censoring, study duration, and patient recruitment periods. We
generate a new approximation for the censoring adjustment. In so doing,
we set out an easy way for others to modify our program for other related
power calculations.
Statistics and Data Analysis — Northern
Hemisphere E-1
4:00 p.m.
represent the magnitude of uncertainty about the population effect sizes is
a useful strategy. This paper provides a SAS® macro that uses bootstrapping
to compute confidence intervals for an effect size associated with
mediation analysis. Using SAS/IML®, the macro produces point and interval
estimates of an R-squared effect size. This paper provides the macro
programming language and an example of the macro call and output. The
results from a simulation study investigating the accuracy and precision of
the estimates are presented.
Statistics and Data Analysis — Northern
Hemisphere E-2
4:30 p.m.
A Bootstrapped Kappa Statistic for a Multiple-Rater
Multiple-Category Problem
Yubo Gao, University of Iowa Hospitals and Clinics
Paper 323-2012
In many research fields, kappa coefficient is a popular tool for measuring
the degree of agreement between two or more raters where the raters rate
the subjects on a categorical scale. SAS® procedures and macros exist for
calculating kappa and its confidence interval. But this is a one-time
calculation. Sometimes, there is a need to estimate the precision of this
statistic through a resampling technique such as bootstrap so as to get a
full understanding about its confidence interval. There is no literature so far
about calculating kappa confidence intervals using bootstrap resampling
methodology in a multiple-rater multiple-category situation. This article
just wants to fill this gap using the SAS procedure PROC SURVEYSELECT and
a macro.
Statistics and Data Analysis — Northern
Hemisphere E-1
4:30 p.m.
Using SAS® to Extend Logistic Regression
Dachao Liu, Northwestern University
Paper 317-2012
Logistic regression is widely used in the analysis of categorical data,
especially data with variables that have binary responses. It can be used in
many fields where discrete responses and a set of explanatory variables
coexist. For example, it can be used in survival analysis, which often uses
data with variables having values of SUCCESS and FAILURE. Logistic
regression can do more by extending it. This paper discusses when and
how to extend logistic regression using SAS®.
A SAS® Macro for Computing Point Estimates and
Confidence Intervals of Effect Sizes Associated with
Mediation Analysis
Merlande Petit-Bois, University of South Florida
Thanh Pham, Measurement and Research Department
Eun Baek, University of South Florida
Jeffrey Kromrey, University of South Florida
Paper 316-2012
Measures of effect size communicate information about the strength of
relationships. Such information supplements the reject or fail to reject
decision in hypothesis testing. Because sample effect sizes are subject to
sampling error, computing confidence intervals for these statistics to
Statistics and Data Analysis — Northern
Hemisphere E-2
Systems Architecture and Administration —
Northern Hemisphere E-3
5:00 p.m.
10:30 a.m.
Using SAS® and LaTeX to Create Documents with
Reproducible Results
Tim Arnold, SAS
Warren Kuhfeld, SAS
Zen and the Art of SAS Maintenance: Maintaining and
Upgrading a Well-Oiled SAS Deployment
Donna Bennett, SAS
Shannon Leslie, SAS
Jason Losh, SAS
Mark Schneider, SAS
Jane Stovic, SAS
Paper 324-2012
Reproducible research is an increasingly important paradigm, and tools
that support it are essential. Documentation for many SAS analytical
products has long been created from a single source system that embeds
SAS code in LaTeX files and generates statistical results from those files. This
system is now available to SAS users as an open source package, which is
similar in spirit to Sweave (Leisch 2002) and SASweave (Lenth 2007). A
script parses the source and generates the SAS program file, which includes
SAS macros that use the ODS document for capturing the output as
external files. Listing and Graphic tags display the captured tabular and
graphical output. This paper describes how to access and implement the
package, and it illustrates typical usage with several examples.
Statistics and Data Analysis — Northern
Hemisphere E-1
5:00 p.m.
Monitoring the Variation in Your Multivariate Process:
An Introduction to the MVPMODEL and MVPMONITOR
James Christian, SAS
Bucky Ransdell, SAS
Paper 318-2012
Complex processes in modern manufacturing and business environments
can generate hundreds and even thousands of process measurements that
vary over time. Early detection of process instability is critical for avoiding
costly failures and minimizing risk. When the process measurements are
correlated, multivariate statistical process monitoring methods are
appropriate. Three new procedures in SAS/QC® 12.1, the MVPMODEL,
MVPMONITOR, and MVPDIAGNOSE procedures, implement methods that
are based on a principal components approach to process monitoring,
which was developed in the field of chemometrics. They provide T 2 and
SPE charts, which are multivariate summaries of process variation. An
example from social media sentiment analysis illustrates how the
procedures work together and demonstrates the power of the methods for
discovering and diagnosing unusual variation.
Paper 354-2012
As a SAS Administrator, you are responsible for managing changes to your
deployed SAS environment. You likely have questions about best practices.
How can I keep track of the SAS hotfixes and maintenance releases? How
often should I apply them? What happens when I run the tools? What are
the best practices that I need to do to make sure that changes will not
negatively impact my production SAS system? Learn about tips and tools
for managing change. Has that hotfix you have just read about been
applied to your SAS deployment? What is the difference between
uninstalling and unconfiguring? Develop a checklist for different types of
changes: applying hot fixes and maintenance, upgrading software versions,
adding SAS software, and moving to different hardware.
11:30 a.m.
SAS® In-Database Capability: Smart Architecture
Gaurav Agrawal, American Express
Paper 355-2012
SAS capabilities are well-recognized throughout the industries, and
businesses are getting valuable information from the data using SAS
capabilities. However, day-by-day data is increasing in industry, and this is
posing an urgent need of not only for a perfect architecture but also smart
thinking to work effectively and efficiently. SAS recognized this fact long
ago and worked dedicatedly toward bringing innovative solutions to
customer. SAS In-Database processing also one of the smart concepts to do
analytics work and provide extremely valuable benefits to industries in
time. Using this methodology, not only Server resource utilizations can be
decreased but this methodology also enable industry to reduce time to
market, which is one of the critical factors in current completive
12:00 p.m.
Another Way to Use SAS® to Monitor SAS or a SAS
Server: A Tool for the User, Server Administrator, or
LeRoy Bessler, Bessler Consulting and Research
Victor Andruskevitch, Valence Health
Paper 356-2012
The administrator or manager of a SAS server, whether BI or non-BI, has
questions. Who is using SAS and in the past, and how much of its resources
(CPU, memory, or I/O)? How heavily does each use the server in terms of
frequency or resources? The user, whether SAS is running on a remote
server or on his/her own PC, has questions. What SAS processes do I have
running? What resource consumption is making my process run so long? By
tapping into a no-additional-expense technology built into Microsoft
Windows, this paper enhances the UserMon tool presented in 2009.The
CPUmon tool presented in 2010 could also be enhanced to send real-time
email alerts for overloads on resources other than processor time.
2:00 p.m.
Top Ten SAS® Performance Tuning Techniques
Kirk Lafler, Software Intelligence Corporation
Paper 357-2012
Base SAS® provides users with many choices for accessing, manipulating,
analyzing, processing, and producing data and results. Partly because of the
power offered by SAS and the size of the data sources, many application
developers and users need guidelines for more efficient use. This
presentation highlights my personal top ten list of performance tuning and
coding techniques for SAS users to apply in their applications. Attendees
learn about SAS language statements and options used in the DATA step
and the PROC step to help conserve CPU, I/O, data storage, and memory
resources while accomplishing tasks involving processing, sorting,
grouping, joining (merging), and summarizing data.
4:00 p.m.
Red Hat Enterprise Linux: Optimizing Your SAS®
Douglas Shakshober, Red Hat
Barry Marson, Red Hat
Mike Guerette, Red Hat
(Invited) Paper 360-2012
Running SAS on Red Hat Enterprise Linux (RHEL) has become more
compelling than ever, and the number of SAS deployments on RHEL has
grown significantly since the last SAS® Global Forum. During this time,
engineers from both Red Hat and SAS (plus several OEMs) have worked to
achieve new performance results with SAS and RHEL to obtain even better
price/performance than before. One configuration even exceeded 8GB/sec
I/O throughput! This session discusses how to optimize your performance
and scalability for running either SAS® Foundation or SAS® Grid Manager
deployments on RHEL. New benchmark results are shared which address
traditional deployments, SAS in virtual machines, and SAS Grid Manager.
We cite recent customer deployments as well.
2:30 p.m.
5:00 p.m.
Security Hardening for SAS® 9.3 Enterprise BI Web
Heesun Park, SAS
Storage 101: Understanding Storage for SAS®
Bob Augustine, Hewlett-Packard
Paper 358-2012
Paper 416-2012
Web configuration for SAS 9.3 Enterprise BI Web applications needs to be
secured to the organization's security policy. This paper examines the Web
configuration security enhancement options and the protection of Web
applications from security vulnerability attacks. Security enhancement for
the configuration includes single sign-on, integration with reverse proxy
security server, setting up of firewalls, use of SSL and building FIPS 140-2
compliant configuration. Implementation of SAS 9.3 Web application
protection mechanism for vulnerability attacks is explained along with the
testing process based on OWASP Top 10 list and IBM AppScan penetration
testing tool.
If the I/O subsystem is not designed and implemented correctly, SAS
doesn't perform as well as it could. This discussion will include:
3:30 p.m.
Schedule Your SAS® Jobs and Go with the Flow:
Maximize the Use of SAS with the Platform Suite
Laura Liotus, Community Care Behavioral Health
Paper 359-2012
Creating a SAS job flow with Platform Suite for SAS in a Microsoft Windows
environment allows one to run processes unattended. SAS jobs are created
and deployed in SAS® Data Integration Studio. Job flows are designed and
scheduled in SAS® Management Console. These flows are run using
Platform Suite for SAS which includes Platform Process Manager and LSF.
The flows are created with dependencies that include a job completion
status, file arrival, or file existence. With a thoughtful plan, the user can get
creative with the dependencies in SAS Management Console and the flow
capabilities of Platform Process Manager. An added feature of all of the
tools includes job status notification. With proper design and planning, one
can use technology to automate their SAS processes.
• Rules of thumb for I/O requirements.
• SAS I/O characteristics.
• Various file systems and their performance.
• How to test file system performance prior to loading SAS.
• How to measure file system performance.
• Understand shared file system protocols and performance. Examples
include CIFS, NFS, StorNext, and others
5:30 p.m.
Integrating SAS with ERwin to Capture Design and
Business Metadata
Jim Ferrari, Valencia College
Juan Olvera, Valencia College
Paper 362-2012
Do you have difficulty documenting architectural or design ideas? Are
naming standards and consistency throughout the data warehouse difficult
to maintain? Do related fields (or even the same field) have unrelated
names in different areas of the data warehouse? A modeling tool like ERwin
can assist with some of these issues. But how do you integrate a modeling
tool like ERwin with your SAS BI environment? Come and learn data
architect and modeling techniques that will help refine your ideas. Learn
how to integrate the metadata from ERwin (or similar tool) into your SAS
environment. The metadata can be extracted into tables for reporting
purposes (data dictionary, requirements, etc) or imported using a metadata
bridge to populate the SAS metadata directly for data target tables.
Travel, Hospitality and Entertainment — Northern
Hemisphere E-4
2:00 p.m.
Are You Awash in the Sea of Competitive Price
Intelligence? Let Analytics Be Your Life Raft
Alex Dietz, SAS
Natalie Osborn, SAS
Tugrul Sanli, SAS
Paper 379-2012
Now more than ever, your guests have access to an ocean of hotel price
intelligence on the Web and are using your rates in context of your
competitors to make their buying decisions. As a result, your competitors’
rates can have a direct impact on the demand for your hotel. So you collect
the data on your competitors’ rates. But, hotel pricing is hard enough
without struggling to account for your competitors’ price strategy.
Overreact to your competitors’ pricing and you can trigger a price war;
underreact and be caught in a spiral of decreasing demand for your hotel.
This paper describes how to leverage analytics with your competitor rate
data to make better pricing decisions for your hotel.
3:00 p.m.
Revenue Assurance: Using SAS® to Identify Revenue
Ahmed Darwish, DIRECTV
Sunil Goklani, DIRECTV
Paper 381-2012
Would you be able to convince your CFO that all revenue and cost streams
are free of monetary leaks? That all people, processes and systems are
designed and executed correctly and that design oversights, system
defects, and human mistakes fail to make their way into the organization?
In a customer oriented industry, ramifications of allowing such anomalies in
the organization could result in a poor customer experience, strained
relationships with vendors, and uncaptured revenue. With several
components interacting in a large organization, SAS® becomes an
invaluable tool for identifying and quantifying these anomalies.
3:30 p.m.
Leveraging Analytics in Transportation to Create
Business Value
Vijitha Kaduwela, Kavi Associates
Paper 383-2012
In this paper, we discuss how analytics is leveraged in the transportation
industry to create business value. The real-life case studies presented in this
paper cover rail, trucking, and airline. In each case study, we discuss the
business problems, the specific applications of analytics to solve the
business problems, and the business value created in the process. We
discuss the descriptive and predictive analytics developed and how they
are used by the customers to gain a competitive advantage by optimizing
capital expenditure, reducing operating costs, improving profitability,
improving reliability, reducing risks, and achieving compliance. We discuss
the specific SAS® solutions and products used for solving these business
4:00 p.m.
Factoring Upgrades into Overbooking Decisions for
Hotels and Casinos
Alex Dietz, SAS
Natalie Osborn, SAS
Tugrul Sanli, SAS
Paper 384-2012
Overbooking is a must for any business that accepts reservations and
subsequently runs the risk of cancellations and no-shows. In hotels, the
practice of overbooking requires a fine balance between guest service,
operational procedure, and revenue optimization. For hotels with multiple
room types, the complexity is multiplied. Adding new room types allows
you to reach a broader market, but every new room type added increases
the risk of underutilized rooms. An overbooking strategy that properly
accounts for upgrades helps you make better decisions on pricing,
inventory control, and overbooking. This paper explores a methodology
and the benefits from factoring upgrades into overbooking decisions for
hotels and casinos.
5:00 p.m.
Implementation of a Restaurant Revenue Management
System at Walt Disney World
Haining Yu, The Walt Disney Company
Frederick Zahrn, The Walt Disney Company
Hai Chu, The Walt Disney Company
(Invited) Paper 382-2012
In February 2009, the Food & Beverage Revenue Management System (F&B
RMS) went live at Walt Disney World (WDW). F&B RMS is thought to be the
first system in production use for optimized generation and allocation of
restaurant reservation inventory. F&B RMS includes a sophisticated demand
forecasting module, a module generating reservation inventory, and a
module producing capacity control parameters. Each of these key modules
was programmed using SAS®. Forecasts, authorized inventory, and control
parameters are dynamically adjusted throughout a 180-day booking
horizon. Disney has implemented a number of improvements to the system
since its introduction, including the integration of a SAS/OR® solver with the
inventory generation module. As of the end of fiscal year 2011, 41 WDW
restaurants are managed through F&B RMS
Walt Disney World Swan and Dolphin Resort
Andrew T. Kuligowski, Conference Chair
Continue your learning and networking opportunities all year long
with—the collaborative online community for
SAS users worldwide. Sponsored by the SAS Global Users Group
Executive Board, was created by SAS users for
SAS users. Here you can publish articles, upload presentations,
create a blog, find SAS code and join in peer-to-peer discussions.
You will find the “sasCommunity Tip of the Day” on the Main Page—
and instructions on how to sign-up to receive the Daily Tip via Twitter!
With thousands of registered members, the community continues to
thrive and grow. We invite you to explore and
contribute to
Applications Development — Southern
Hemisphere V
8:00 a.m.
A Guide for Connecting Java to SAS® Data Sets
Ryan Snyder, Institute for Advanced Analytics
Johnston Hall, North Carolina State University
Paper 008-2012
This paper is written for Java programmers who want to access SAS data
sets. We provide step-by-step examples to connect Java to SAS using three
SAS technologies:
• the Base SAS® Java Object interface (Javaobj)
• SAS/ACCESS® to a third-party database The first example sets up a Java
class and then drives it from Base SAS. The second and third examples
build a simple Java applet and then use Java Database Connectivity
(JDBC) code and driver to read data from a server. Each example is based
on the Windows operating system using the sashelp.class sample data
8:30 a.m.
Integrating Your Java Web Application into the SAS® 9.2
or SAS® 9.3 Enterprise Business Intelligence
Guillaume Curat, SAS
Paper 009-2012
Do you want your existing Java Web application to look and behave like
other SAS applications? The key to achieving this goal is the use of the SAS
Logon Manager, SAS metadata roles and capabilities, SAS themes, the SAS
Logging Facility, and metadata. This paper explains in detail all of the steps
necessary to integrate your Java Web application to an existing SAS
enterprise business intelligence (BI) environment. SAS® AppDev Studio is
used to demonstrate how easily it can be done.
9:30 a.m.
Get Your "Fast Pass" to Building Business Intelligence
with SAS® and Google Analytics
Patricia Aanderud, And Data Inc
Angela Hall, SAS
(Invited) Paper 010-2012
See the magic of Google Analytics with SAS® business intelligence tools!
Use your "Fast Pass" to learn SAS® Information Map Studio, SAS® Web
Report Studio, and SAS® Information Delivery Portal with the authors of the
newly released "Building Business Intelligence with SAS®". We will guide
you step-by-step through creation of information maps, custom web
reports, and portal pages using data from Google Analytics. You will learn
some tips and tricks for creating custom data items, designing and linking
reports, and adding external content to your portal.
10:30 a.m.
Mobilizing Your SAS® Business Analytic Reports
Falko Schulz, SAS
Paper 011-2012
This paper explains the steps involved in getting your SAS® Stored
Processes published to mobile devices such as iPhones and iPads. Specific
HTML markup and JavaScript techniques allow a seamless integration of
SAS® output to be rendered on mobile devices. Considering the smaller
screen real estate and input gestures an intuitive touch-and-swipe user
interface is used. This mobile interface allows the user to quickly browse for
the desired stored process and view the rendered output. The paper
provides an example toolkit including source code which can be used to
get your business reports mobilized.
11:30 a.m.
Tracking and Reporting Account Referral Activity Using
Hash Tables and SAS® Business Intelligence
James Beaver, Farm Bureau Bank
Tobin Scroggins, Farm Bureau Bank
Paper 012-2012
This paper demonstrates how Farm Bureau Bank uses the SAS® hash object
and the SAS hash iterator to track and report on new account referrals. New
account referrals are tracked by agent representatives based on their
location, sales territory, and manager. To handle these needs, an agent
dimension table is created as part of a data warehouse. Examples show the
use of the SAS hash object methods FIND(), REPLACE(), and OUTPUT() to
add new records and overwrite and partition existing records in the agent
dimension table. An example of the hash iterator and use of the LAST()
method illustrates how to determine the last key in the table. Sample
reports using SAS BI tools, including OLAP cubes and SAS® Web Report
Studio, are demonstrated.
1:30 p.m.
Yes! SAS® ExcelXP WILL NOT Create a Microsoft Excel
Graph, but SAS Users Can Command Microsoft Excel to
Automatically Create Graphs from SAS ExcelXP
William Benjamin Jr, OWL Computer Consultancy,LLC
Paper 013-2012
The SAS ODS Tagset ExcelXP creates *.xml output, and *.xml output cannot
contain graphs. So how can SAS programmers get graphs into your Excel
workbooks? One way is to build them in Excel yourself. This paper shows
you how to create data using SAS, and then command Microsoft Excel to
read the data, create a graph or fully reformat a worksheet, without putting
an Excel macro into the output Excel Workbook. And the program will do it
all while you watch, including for multiple sheets in a workbook. The SAS
code, and Excel code, shown is a fully integrated system to create and
format macro-free Excel workbooks, using SAS® 9 (SAS® 8 if Internet
downloads are available) and Excel 97 and above.
2:00 p.m.
4:00 p.m.
Excel with SAS® in .Net
Steve Gunawan, Wyndham Exchange & Rental
SAS® IOM and Your .Net Application Made Easy
Karine Désilets, Statistics Canada
Paper 014-2012
Paper 017-2012
SAS® Integration Technologies enables software developers to leverage the
analytical power of SAS from other applications in their organization. The
Integrated Object Model (IOM) makes it easy for many industry-standard
technologies to access and use SAS software features on cross-platform
environments. In this paper, we will see how combining point-and-click
interface with SAS and Microsoft Excel automation allows Wyndham
Exchange & Rentals to effectively build a user-friendly decision support
application for its business users.
At Statistics Canada, many statistical systems are implemented in a clientserver development context allowing maximum use of SAS® tools, software,
and solutions. This article focuses on development of Microsoft .Net client
applications using SAS Integrated Object Model (IOM) to take advantage of
the processing, analysis, reporting and data storage power of SAS. This
article covers a number of best practices such as the different
communication modes between Microsoft .Net and SAS, types of SAS code
execution, parameter management, libref and fileref management, error
management with raised event, data acquisition via Ado.Net, automated
analysis of SAS log files and management of customized return codes
between SAS and Microsoft .Net. Finally, a few broader topics associated
with this work and future research projects are addressed.
2:30 p.m.
Custom Analysis and Reporting with the JMP®
Application Builder
Daniel Schikore, SAS
Paper 015-2012
The JMP Application Builder is a drag-and-drop environment for custom
application development. Developers have access to the full capabilities of
JMP, including more than 50 analysis and graphics platforms for in-memory
analytics, as well as custom scripting with JSL to connect to SAS for more
powerful techniques. Custom, multi-window reports can be created
interactively without having to write scripts at all. A flexible, hierarchical
data filter allows the developer to apply filters to all or parts of a report. The
developer can deploy a JMP Application for other JMP users to run,
optionally encrypting the application with a password required to run the
3:30 p.m.
Automated Process for Routine Clinical and Safety Data
Monitoring Reports: An Integration of EDC Database,
Microsoft Outlook, and SAS®
Songtao Jiang, Boston Scientific
Hsini Liao, Boston Scientific Corporation
Paper 016-2012
In the pharmaceutical or the medical device industry, routinely reporting
clinical and safety data is required to meet the ICH Guideline for Good
Clinical Practice. However, the repeated report production per se is
sometimes time-consuming and requires a significant amount of resources.
Therefore, an innovation for improving the current reporting process is
always a demand. An automated process leveraging the integrating
features of an electronic data capture (EDC) database, Microsoft Outlook,
and SAS is proposed. Specifically, a completely data-driven process for
generating routine reports by using Visual Basic Application (VBA) codes
incorporated with moderate SAS coding is deemed cost-effective. The
process can be applied to any industry where a programming professional
is equipped with Microsoft Outlook and SAS as a working platform.
4:30 p.m.
Integrating Enterprise Search with Various Clients
Arvind Jagtap, SAS
Paper 018-2012
In today’s world of information technology, the information is exploding
through the internet. Search has become an integral part of life. Enterprise
contents are no exception and the enterprise search plays a major role in
finding the required information quickly to enhance the productivity of
business executives. A need for searching “Enterprise Objects” can arise at
any time while working with some popular applications. Hence, integrating
search features with these applications can be helpful. As a part of SaaS,
SAS provides “Search Interface to SAS Content” as a service for searching
enterprise contents. This paper demonstrates how this service can be
invoked from frequently used applications like Microsoft Office or any Flex/
Java client to allow users to search the required contents without leaving
the application.
Applied Business Intelligence — Northern
Hemisphere A-4
8:00 a.m.
SAS® OLAP Cube Tuning and Query Performance
Tatyana Petrova, SAS
Paper 026-2012
SAS® OLAP Server provides a powerful engine for processing
multidimensional queries to bring SAS OLAP users quick answers back to
their analysis requests. This engine's power relies on well-defined and
properly tuned OLAP cubes. A cube should be designed keeping users'
analytical needs in mind while following best practices for hierarchies and
facts organization. As analysis patterns evolve over time, cube aggregations
should be periodically realigned to provide the best foundation for
querying processing. Luckily, with SAS tools, it is not hard to ensure that
your OLAP tuning is up-to-date. This paper helps advanced OLAP users and
administrators analyze OLAP cubes’ usage and tune cubes’ aggregations
set. It also covers common factors that impact querying performance and
tips for query processing troubleshooting.
9:00 a.m.
11:00 a.m.
Custom Rollup: When the Cube’s Default Behavior
Doesn’t Do the Right Job!
Paresh Patel, Shlomish Consulting,Inc
Making it Happen: Using SAS® to Implement Business
Intelligence and Analytics in Small and Midsize
Richard Hallquist, SAS
Dragos Coles, SAS
Lorrie Gallego, SAS
Paper 027-2012
Aggregation tables are viewed more in terms of cube data storage and
query performance but can also be used to satisfy business queries by
creating custom rollup. Aggregation tables are built to define data in the
cube that is available to satisfy query requests without having to
summarize the data on the fly. An important aspect of cube design is cube
granularity. When the cubes rolls up to wrong numbers it’s simply wrong.
“Very wrong. In practice, people like Business Managers can get surprisingly
tense about this kind of error, and you end up getting aggravation about
your aggregations.” This paper presents a practical challenge encountered
during rolling up a cube data with attributes having many-many
relationship in a cube and resolved using aggregated tables.
Paper 030-2012
Business intelligence and analytics often seem to be the domain of large
organizations with deep pockets. This paper abolishes that myth and shows
you how you can get started in much smaller settings. Whether you are a
midsize company or a small group within a larger organization, using SAS
to implement business intelligence and analytics is an achievable goal. We
use real-world scenarios to demonstrate how to extract and share insight
from your data. This includes:
• formulating your goals
9:30 a.m.
• using SAS® Enterprise Guide® to handle data management
At Your Self-Service: One Organization’s Journey from
Mainframe Reporting to Enterprise Business Intelligence
Cheryl Sivertson, University of Victoria
• using SAS enterprise business intelligence to build a dashboard and a
PowerPoint presentation to show these results
• using SAS/STAT® to build and score predictive models
Paper 028-2012
1:30 p.m.
The University of Victoria’s Project NOVA replaced a number of
technologically dated stand-alone systems with a state-of-the-art
information technology infrastructure that integrates Student, Human
Resources, Finance/Accounting, Alumni, and Facilities Management
components. The change in infrastructure required the replacement of
hundreds of mainframe reports that supported a variety of operational and
strategic reporting processes. To meet mandatory British Columbia
provincial government accountability requirements, the first priority was to
replace the university’s Student Enrollment Management reporting, which
provided a rare opportunity to reevaluate, reinvision, and restructure all
student-reporting processes. This paper discusses the journey from product
selection to production SAS® Enterprise BI Server Web portal
implementation and every step in between. Challenges faced, benefits
achieved, tips learned, and future steps are presented.
Using SAS® Enterprise BI and SAS® Enterprise Miner™ to
Reduce Student Attrition
Matt Bogard, Western Kentucky University
Chris James, Western Kentucky University
Tuesdi Helbig, Western Kentucky University
Gina Huff, Western Kentucky University
10:00 a.m.
Preparing for a SAS® EBI Platform Deployment or
Brian Varney, Experis Analytics Practice
(Invited) Paper 029-2012
Getting a new SAS® Intelligence Platform deployed or migrated is an
exciting time for a company. The promises heard during the sales cycle and
project demonstrations need to become actionable processes by the
administrators, power users, and information consumers once the
installation is complete. The reality is that this can happen only with careful
planning and preparation before, during, and after the SAS platform
installation process. This paper addresses how to plan and prepare for each
phase of a SAS Intelligence Platform deployment or migration so that when
the installation and configuration are complete, the platform can be
leveraged in an organized manner. We assume that SAS Enterprise BI Server
(EBI) software has already been chosen.
Paper 031-2012
The true supremacy of the SAS® Enterprise BI Server is the ability to use the
power of SAS® Analytics to deliver real-time information to users who
usually do not understand statistics, but who have the ability to make a
difference if they have easy access to the analyzed data. This paper
describes the process of using SAS® Enterprise Miner™ to develop a model
to score university students based on their risk of attrition and deliver easy
to understand results to university personnel using SAS® Enterprise BI.
2:00 p.m.
SAS® BI Content Syndication with the REST Framework
Mike Vanderlinden, Experis
Paper 032-2012
This paper discusses a method to make the SAS BI content available to
other parts of your organization through the HTTP protocol. Data,
Information Maps, Metadata, Reports, Stored Processes can be made
available to any system that can talk HTTP, whether it's a browser on your
desktop, a SharePoint website, a mobile device, or anything else including a
competitor's portlet. The REST framework is leveraged to provide the ability
to reach SAS content with a zero-footprint client, as well as a powerful set
of APIs to allow non-SAS developers to create rich interfaces.
2:30 p.m.
Beyond Star Schema: Exploring the Next Query
Generation with the SAS® Enterprise BI Server
Fred Levine, SAS
output. Understanding the behavior of SAS when storing the unformatted
values will help avoid potential mistakes in using formats and nested
classification variables. This paper examines two scenarios when a variable
for both ethnicity and race is used in PROC TABULATE to create an output
data set: (1) with, and (2) without the use of a format.
Paper 033-2012
8:15 a.m.
Structured Query Language (SQL) generation is an essential function of the
SAS Enterprise BI Server that enables consistent, self-service access to data
for many users. This paper explores enhanced ways that the BI server
generates “intelligent” queries with SAS® 9.3. The new Intelligent Query
processor generates SQL based on complex dimensional and relational
data models, while providing users with an easy and unique way of asking
very specific questions about their data.
Increase your OUTPUT with PROC MEANS and PROC
Julie Kezik, Yale University
Melissa Hill, Yale University
3:30 p.m.
Visualizing Data Techniques, Including Autocharting
and Big Data
Justin Choy, SAS
Paper 056-2012
How many people have ‘x and y’? How many people are in category ‘z’? The
questions are endless, but the solutions are not! Using an output statement
in PROC MEANS or PROC FREQ can easily answer those inquiries. The
purpose of this paper is to utilize the OUTPUT statement in PROC MEANS or
PROC FREQ to get simple statistics for a selected variable or group of
variables. The variables in the resulting SAS® data set can be used for future
analyses and/or be easily exported to create graphical or tabular displays.
Paper 034-2012
Visualizing data of varying sizes can be challenging. This paper discusses
the issues concerning visualizing data and provides suggestions on how to
address these issues. The paper assists users who don't know which
visualization to use for their data.
4:30 p.m.
Van Gogh Your Data: Data Visualization Methods with
SAS® Business Intelligence
Natalie Parsons, SAS
Scott McQuiggan, SAS
Paper 035-2012
From the halls of academia to the walls of museums, data visualization is an
art form with ever-increasing prominence. But, how do we take data
visualization concepts from these expert designs and create real-world
business solutions? Using methods from distinguished data visualization
experts and SAS BI, this paper presents contemporary techniques to
visualize your data and simplify over-complicated reports with ample
examples for both novice and expert report writers. We explore the utility
of simplicity in BI reports, design guidelines that capitalize on
understandings of visual perception, and optimizations for report
consumption on various display media. While these techniques are
applicable across industries, we focus our examples on illustrations utilizing
data fundamental to the education industry.
Coders' Corner — Southern Hemisphere III
8:00 a.m.
Ethnicity and Race: When Your Output Isn't What You
Philamer Atienza, Alcon Laboratories, Inc
Paper 055-2012
In SAS®, when a classification variable is used to group observations with
the same values and a formatted value is used for grouping data,
unexpected results may come out of the procedure. If there is more than
one unformatted value used for several distinct categorizations but with
the same format label, SAS uses the unformatted lowest value to create the
8:30 a.m.
A SAS® Macro to Zip and Unzip Files in MS Windows
without Additional External Data Archiving Software
Kai Koo, Abbott Vascular
Paper 057-2012
A SAS macro is developed to compress/decompress files or folders in zip
format without the helps from any third-party zip/unzip applications. It
starts the default Compressed (zipped) Folder function exists in every PC
running under Windows XP or later version through a short VBScript code
activated by SAS %sysexec macro statement. This approach eliminates the
dependence of installation of additional auxiliary files or external zip/unzip
software, and it enhances the portability of SAS programs at different
machines or working environments.
8:45 a.m.
Inventory Your Files Using SAS®
Brian Varney, Experis Analytics Practice
Paper 058-2012
Whether you are attempting to figure out what you have when preparing
for a migration or you just want to find out which files or directories are
taking up all of your space, SAS is a great tool to inventory and report on
the files on your desktop or server. This paper intends to present SAS code
to inventory and report on the location you want to inventory.
9:00 a.m.
Locally Visible, Remote Data and Format
Hsiwei Yu, Custom Software Systems
Kamau Njuguna, Lockheed Martin
Paper 059-2012
When in a workplace environment with mixed platforms, sooner or later
one will come across the need to work in or access files in a host that is in a
different environment. This paper shows how to make remote data
available in the local environment. This way, one can perform interactive
tasks such as browsing and querying as if everything is local, at one’s
fingertip, for more productive work.
9:15 a.m.
10:00 a.m.
Standardized Macro Programs for Macro Variable
Chris Swenson, UW Health
Deciphering PROC COMPARE Codes: The Use of the
bAND Function
Joseph Hinson, Merck & Co., Inc.
Margaret Coughlin, Merck & Co., Inc.
Paper 060-2012
Creating macro variables for later use can help to create dynamic, powerful
SAS® programs. Creating those variables in a standard, consistent manner
without causing any conflicts with other macro variables, however, can be
repetitive, time consuming, and prone to error. Here we present macro
programs that assist with generating macro variables with the intent to use
the variables in specific ways later in the program. Each macro meets a set
of criteria including allowing the filtration of input data (if possible);
deleting conflicting macro variables; creating macro variables in a
consistent, predefined manner; and reporting the result of the macro’s
9:30 a.m.
How to Use SAS/CONNECT® to Get Your Mainframe to
Behave Like a Modern Computer in Your New Business
Intelligence Platform
John Hennessey, Social Security Administration
Paper 061-2012
This paper reports on the ability to embed SAS/CONNECT® code in a stored
process on a SAS® Business Intelligence (BI) platform. The Social Security
Administration’s Office of Research, Evaluation, and Statistics (ORES) has a
BI platform installed on a Windows server to produce summary statistics
and data extracts for the analysis of Social Security programs. The BI
platform must communicate with large mainframes to access and process
the operational data of the Social Security Administration. Since 2006, we
have been developing ways to use SAS® Enterprise Guide® and SAS/
CONNECT® to bring the mainframe into a modern interface. We are
currently developing stored processes that can be used by our internal
customers to run directly without ORES intervention.
9:45 a.m.
A Macro to Summarize and Generate a Report of
Variables on a SAS® Data Set
Greg Grandits, University of Minnesota
Greg Thompson, Division of Biostatitics, University Of
Paper 062-2012
Before starting analysis of data from a SAS data set, it is useful to have
documentation and summary information of each variable before you
begin working with the data set. We have developed a macro that
generates a report summarizing each variable on a data set, one line per
variable, which includes both numeric and character variables, and formats
date variable statistics with date formats. A nicely formatted report is
generated that gives the user a good understanding of the data set and is a
useful reference when beginning to write SAS programs using the data set.
Paper 063-2012
The COMPARE procedure is very useful for validating SAS® data sets in
clinical studies. One particularly useful feature is its SYSINFO system macro
variable by which numerical codes are issued following the comparison of
data sets. These codes represent up to 16 messages that describe the
outcome of the comparisons. Thus, interpreting SYSINFO codes can provide
a very concise PROC COMPARE report, especially when many pairs of data
sets are involved. In this paper, we demonstrate a novel approach for
decoding SYSINFO values using the SAS function bAND (bitwise logical
AND). With this function, one can quickly determine which of the 16 PROC
COMPARE output messages a SYSINFO code contains.
10:15 a.m.
Assigning a User-Defined Macro to a Function Key
Mary Rosenbloom, Edwards Lifesciences, LLC
Kirk Lafler, Software Intelligence Corporation
Paper 064-2012
Are you entering one or more of the same SAS® Display Manager System
(DMS) commands repeatedly during a session? The DMS offers a
convenient way of capturing and saving frequently entered commands in a
user-defined macro, and then saving the macro as a function key of your
choosing. Are you typing SAS® code for data exploration during program
development or validation, only to delete it soon afterwards? If you are,
then this code can be placed in a macro, too, and assigned to a function
key. This paper illustrates the purpose and steps that you use to assign a
user-defined macro to a function key.
10:30 a.m.
Using Pre-Formatted Microsoft Excel Templates with
George Mendoza, CIGNA
Subhashree Singh, The Hartford
Paper 065-2012
SAS has several different options for transferring data to Microsoft Excel.
However, exporting data into a pre-formatted Excel template consisting of
predesigned tables and charts can be challenging. Usually, there is some
manual intervention required particularly in a UNIX environment. The
solution to leveraging pre-formatted Excel templates in a server
environment is the use of SAS® Integration Technologies to serve as a
bridge between Base SAS® and the Excel template. This paper will walk you
through the steps required to set up this bridge so that you can begin to
use Excel templates together with SAS in an auto-mated server
10:45 a.m.
11:45 a.m.
Create Multi-Sheet Excel Workbook for Large Data Sets
by SAS® and VBA
Chao Huang, Oklahoma State University
Techniques for Generating Dynamic Code from SAS®
Jingxian Zhang, Quintiles, Inc.
With fast-growing data volume, transforming large data sets from SAS to
multi-sheet Microsoft Excel workbooks becomes challenging. In addition,
more than one grouping variables may be specified to separate a SAS data
set to sheets in an Excel workbook. This paper describes a new and fast
solution to create multi-sheet Excel workbooks, which also allows multiple
grouping variables for each sheet. Two examples with SAS’s help data sets
will be used to illustrate how to use ODS HTML destination and a VBA script
to produce Excel workbook. This two-step approach can process very large
SAS data sets for multi-sheet Excel reporting in a short time. It is also
customizable for special needs such as traffic lighting.
Integrating the information from SAS DICTIONARY tables into
programming helps create dynamic and efficient scripts to manage data
sets. The purpose of this paper is to provide such techniques for generating
dynamic code from SAS DICTIONARY tables. The author uses three macros
to demonstrate how DICTIONARY tables-driven code is dynamically
constructed via three approaches: SQL select into macro-variable method,
call execute method, and generate-and-include an external file method.
These macros manage all data sets at the library level: capitalize all
character data, dump all data into an excel file, and query all character data
with certain length. Using the basic techniques discussed in the paper, SAS
programmers can develop their own dynamic scripts to accomplish other
Paper 066-2012
11:00 a.m.
Excel Tool for Coding
Ronald Palanca, Mathematica Policy Research, Inc.
Paper 067-2012
Open–ended coding is the method of assigning numeric values to verbatim
questionnaire responses for the purpose of categorizing the responses for
analysis. To perform this task, coders go through the list of verbatim
questionnaire responses, and then refer to another list for the assigned
numeric values to determine which value to assign. This paper presents a
cost-effective way to set up a front end for the coders to do the coding by
using a SAS® data set. An Excel spreadsheet with the actual question, the
verbatim questionnaire responses, and the lookup codes is created in the
same worksheet, and each sheet is categorized by question number. There
is no need for a predefined template.
11:15 a.m.
Paper 070-2012
1:30 p.m.
ODS Report Writing Interface Makes Our Reporting
Simple and Better
Sijian Zhang, University of Alabama at Birmingham
Paper 071-2012
When we feel that a complex report cannot be generated directly from
SAS®, we usually get the data or some report components prepared in SAS,
and then use other software, such as Microsoft Word or Excel, to finish the
reporting job. This situation has been changed since SAS® 9.2. Taking one of
our routine reports as an example, this paper illustrates some useful
features that the ODS report writing interface has, how syntaxes are
applied, and how a complicated report can be done with simple code. With
this new tool, our complex reports can be generated by just running the
SAS program, which is much smoother and more efficient.
PROC REPORT: Dynamic Column Headings
Jason Levy, PPD
1:45 p.m.
This paper shows a technique to dynamically make a column header that is
independent of the data in the column itself. It also uses one macro variable
to subset the data and to create the column header.
Paper 072-2012
Paper 068-2012
11:30 a.m.
Splitting Data Sets on Unique Values: a Macro That Does
It All
Hans Sempel, Belastingdienst
Paper 069-2012
Sometimes it is necessary to split a data set into multiple data sets,
depending on the unique values of a variable. After this task was requested
several times at the Belastingdienst in the Netherlands, a macro was
developed that could split every data set based on a variable. The results
are a data set for every unique value of that variable. And, all it took was
two DATA steps!
Finding Your Way Around a SAS® Generated Report
William Murphy, Howard M. Proskin & Associates, Inc.
Using the procedures of the SAS system, we can and do generate hundreds
of tables. The Output Delivery System easily renders these tables in rich text
format. Navigating around the resulting report would be quite daunting if
not for the Microsoft Word Table-of-Contents tool. Before you can use this
tool profitably, careful attention must be paid to the Word settings and the
SAS program that creates the tables. Appropriate use of the CONTENTS
option and the ODS PROCLABEL statement must be made to achieve a
useful result. Using these options along with PROC REPORT, we will
demonstrate how to generate a clear and definitive table-of -contents in
your report. This method will then be extended to other procedures, like
2:00 p.m.
Let the DATA Step Drive the Report Assembly Line
Sijian Zhang, University of Alabama at Birmingham
Paper 073-2012
Our data quality assurance (QA) reports are sent out to more than one
hundred hospitals periodically. All reports have the same components with
the information customized to each hospital. The components were
assembled for each hospital one by one manually before. Running some
simple code in the DATA step, we can speed up the process significantly. It
works like generating the reports in an assembly line with limited
programmer’s intervention.
2:15 p.m.
Uploading Your IPEDS Data Electronically Using SAS®
James Hume, Western Kentucky University
Paper 074-2012
This paper demonstrates how to use SAS® code to produce a text file that
can be used to electronically upload data to the IPEDS Completions Survey.
Universities have to provide a large amount of completion data to IPEDS,
and this can be a time-consuming task if data is manually entered in the
system. Using a few DATA steps, this paper shows you how to upload all of
your completion data in a matter of minutes, saving you a tremendous
amount of time.
2:30 p.m.
3:00 p.m.
Using DDE and VBA Techniques to Import Data from
Microsoft Word Tables in Programming Specification
Files into SAS
Mei Li, Novartis Pharmaceuticals Corporation
Zemin Zeng, Forest Research Institute, Inc.
Paper 077-2012
This paper will introduce a SAS application with Microsoft Word for
selecting table data in Word files and importing data from Word tables into
SAS. Dynamic Data Exchange (DDE) and Visual Basic for Application (VBA)
techniques used in the application will be presented in great detail. The
application significantly improves the efficiency and sustainability of
automatically converting Word tables to SAS data. The application is widely
used at work for programmatically retrieving the comments from the
programming specification files during the creation of Data Definition
documentation (define.xml/define.pdf) for New Drug Application (NDA)
electronic submissions.
A Simple Way of Importing from a REST Web Service into
SAS® in Three Lines of Code
Philip Busby, SAS
3:15 p.m.
Think old programmers can't learn new tricks? In this paper, I show two
neat tricks that combine into something really clever. (1) Our first neat trick
is that instead of a path to a file on disk, the filename statement can also
accept a URL (via the URL Access Method). (2) Second, the SAS XML
Libname Engine (SXLE) can read in a static XML document from a filename
statement and turn it into a table. Combining these two, you can have SAS
download a dynamically generated XML document, probably produced by
a REST web service (which can be built in Java or PHP or .NET; it doesn't
matter), and you can do it all in three lines of code.
Paper 078-2012
Paper 075-2012
2:45 p.m.
Using SAS® and ZIP Codes to Create a Nationwide First
Responders Directory
Andrew Hummel, Delta Air Lines
Paper 076-2012
SAS can calculate the distance in miles between two points by using ZIP
codes and longitudinal and latitudinal data. This can be used to match
potential disaster areas with the location of first responders based on their
distance from the potential crisis area. Delta Air Lines serves more than 250
airports in the United States and has more than 10,000 pilots residing in all
50 states who could act as first responders. Using each airport’s longitudinal
and latitudinal coordinates along with each pilot’s home ZIP code, a first
responder’s directory can be created listing each pilot living within a
specified distance from each airport. This directory can be used to quickly
match first responders to any emergency location in the United States.
Sending E-mails in Your Sleep
Andrew Hummel, Delta Air Lines
In today’s world of the mobile office it seems that we are never totally
disconnected from the workplace. An increase in global business has added
to the need of always-available 24-hour a day communication. This often
leads to an increase in working hours and a decrease in sleep. But SAS® can
help by running automated programs and sending e-mails with dynamic
data and attachments around-the-clock. SAS can also monitor processes
and send e-mail alerts when a problem is detected. At Delta Air Lines SAS
has increased efficiency through automation and has allowed programmers
to send e-mails while they are literally at home sleeping.
3:30 p.m.
A Perfect Case of Capturing Data from Related Web
Jinson Erinjeri, D.K. Shifflet and Associates
Paper 079-2012
The World Wide Web generates information at a very fast pace and it can
become equally important to capture the data associated with the
information at that pace. This paper deals with an application that captures
the data from related web pages and converts it into a SAS® data set. This
application converts the source code of a web page in text format to a SAS
data set using Base SAS® and the same is applied across related web pages
using SAS macros
3:45 p.m.
PROC FORMAT, a Speedy Alternative to Sort/Sort/Merge
Jenine Milum, Wells Fargo & Co.
Paper 428-2012
Many users of SAS® software, especially those working with large data sets,
are often confronted with processing time challenges. How can one reduce
the amount of CPU required to retrieve specific data? In this paper, an
“outside the box” approach using a matching method utilizing PROC
FORMAT replaces the CPU-heavy Sort/Sort/Merge. It is ideal for situations
when a key from one file is needed to extract data from another file. It is
more apparently useful when at least one of the files is quite large. This
method has been proven time and again to decrease CPU by 70% to 80%
and is effective on all platforms utilizing Base® SAS.
4:45 p.m.
4:00 p.m.
Paper 084-2012
Customizing ODS Graphical Output for SAS/STAT®
Yang Xiao, University of Cincinnati
Xiangxiang Meng, SAS
Paper 081-2012
Many SAS/STAT® procedures can generate graphs based on ODS graphics.
However, in these statistical procedures, there are few options available for
the image configuration of the ODS graphics. In this paper, we discuss three
ways to customize the ODS graphical output from a statistical procedure
including using the built-in PLOTS= option in the procedure statement,
modifying the Graph Template Language (GTL) template used by the SAS/
STAT procedures, and using the ODS style template. The odds ratio plots
and ROC curves produced by the LOGISTIC procedure are used throughout
the examples to introduce these three methods step by step.
4:15 p.m.
How to Measure the SAS® BI Audience and Discover
Information Needs
Plinio Faria, Bradesco
Paper 101-2012
It’s very useful to measure an audience using SAS® Web Report Studio. It
helps you create better reports and know the users' information needs, and
it will guide the development of your reporting system. Many times, there is
too much information available, and users feel that it is too difficult to get
what they really need. It is important to create comprehensive reports and
to keep only those that are being regularly viewed. This presentation shows
how to measure how often a report is accessed using SAS® Web Report
Studio log files, and how to combine this data with user data to classify
users into groups. You can analyze what type of reports should be available
and the way users like to see these reports.
4:30 p.m.
Have Your Web Reports Remember the Filters of Your
Frank Poppe, PW Consulting
Andres Antwerpen, PW Consulting
Paper 086-2012
SAS® Web Report Studio offers several ways of filtering your data. However,
often users would like to define a filter only once, and have this filter
applied automatically when opening different web reports. This paper
describes a way of accomplishing just that: the user makes a selection in
SAS® Information Delivery Portal, which then is stored and applied
automatically to a SAS Information map using the SAS® Stored Process
Server. In this way, each web report that uses this information map will
automatically show source data filtered for the user’s selection.
%SPARKY: A SAS® Macro for Creating Excel Sparklines
Ted Conway, Chicago, IL
Think big? No, think small! Characterized by their small size and high data
density, sparklines are information graphics that present trends and
variations associated with data in a simple and condensed way. This paper
describes %SPARKY, a SAS® macro that creates cell-sized sparklines for
embedding in Excel worksheets. This technique might be of interest to all
skill levels. It uses Base SAS®, SAS/GRAPH®, the SAS® Macro Facility, Excel,
and Visual Basic for Applications (VBA) on the PC platform.
5:00 p.m.
Adding Count as a Data Label in a Scatter Plot
Suneetha Puttabasavaiah, Mayo Clinic
Paper 085-2012
When there are too many data points in a scatter plot, it is useful to have a
Count label instead of showing all of the overlapping data points. Here are
the simple steps to add a statistic as a data label to a graph: 1. Get the
required statistic values for variable 1 and 2. 2. Output the required statistic
values to a data set. 3. Sort the original data set by variable 1 and 2. 4.
Merge the statistic values with the original data set. 5. Use the Datalabel
option in SGPlot to show the statistic as a label.
Data Management — Northern Hemisphere A-2
8:00 a.m.
What's New in SAS/ACCESS® and Process Improvements
That You Apply to Your DBMS
Howard Plemmons, SAS
Michael Ames, SAS
Paper 115-2012
This paper provides an overview of major new features in SAS/ACCESS. It is
also a look at process improvements that can help with DBMS performance.
The information provided will help with SAS execution performance.
9:00 a.m.
Using SAS® to Move Data between Servers
John Bentley, Wells Fargo Bank
(Invited) Paper 116-2012
In today’s data management environments, it is not unusual for UNIX
servers to be dedicated to a particular department, purpose, or database.
As a result, a data analyst using SAS often works with multiple servers, each
with its own data storage environment. Adding complexity, for security
reasons our IT partners often do not make it easy for the servers to talk to
one another. How do we transfer data between servers? SAS provides
several solutions. This paper shows ways to use SAS Data Transfer Services
and Remote Library Services combined with Remote Compute Services to
move data between servers. Code samples are provided. All levels of SAS
programmers and SAS® Enterprise Guide® users working in multiple server
environments should find the paper useful.
10:00 a.m.
1:30 p.m.
Reordering Values within Observations: Beyond CALL
Adish Jain, NORC at the University of Chicago
Kate Bachtell, NORC at the University of Chicago
Developing Custom Metadata Reports for SAS® Data
Integration Studio
Michael Kilhullen, SAS
Paper 117-2012
PROC SORT orders SAS® data set observations by the values of one or more
variables. CALL SORTC/N are new CALL routines in SAS® 9.2 and above that
reorder values within each observation (in ascending order only). In short,
PROC SORT orders data set observations vertically, while CALL SORTC(N)
orders values horizontally within the observation. Although these new
routines can be useful in some situations, this paper deals with a more
complex data management task: multiple groups of variables needing to
be sorted horizontally in descending order. In our case, these groups of
variables are items for every child living in a household, which also must be
linked back to household data using the child’s age and position in the
10:30 a.m.
Applications of PROC GEOCODE and Incorporation of
Census Block-Level Data
John Havens-McColgan, Yale University
Paper 118-2012
PROC GEOCODE is a powerful tool in SAS® with applications in
epidemiological studies that involve geographically restricted exposures
and health outcomes. This paper describes the use and application of PROC
GEOCODE, specific to street-level geocoding. Preliminary steps are
reviewed, and results are presented with a focus on applications of PROC
GEOCODE in an observational study for which data at a census block level
must be incorporated. Applications discussed include determining
eligibility where requirements for the study are geographically limited,
predicting the size of a population of eligible subjects in a geographic area,
analyzing subject demographic characteristics, and comparing information
to census data to ensure representative sampling.
11:00 a.m.
The FILENAME Statement: Interacting with the World
Outside of SAS®
Christopher Schacherer, Clinical Data Management Systems,
(Invited) Paper 119-2012
The FILENAME statement has a very simple purpose—creating a symbolic
link to an external file or device. The statement itself does not process any
data, specify the format or shape of a data set, or directly produce output of
any type; yet, this simple statement is an invaluable construct that allows
SAS programs to interact with the world outside of SAS. Through
specification of the appropriate device type, the FILENAME statement
allows you to symbolically reference external disk files, interact with FTP
servers, send e-mail messages, and integrate data from external programs
and processes—including the local operating system and remote web
services. The current work provides examples of how you can use the
different device types to perform a variety of data management tasks.
Paper 120-2012
SAS Data Integration Studio 4.x includes new functionality that allows you
to run reports through an interactive reporting facility. You can also create
custom reports by using SAS Data Integration Studio software's Java-based
plug-in functionality. The plug-in can be written to generate report content
using SAS code, Java code, or both. This is ideal for developing reports that
specifically address the needs of data integration specialists such as
documenting jobs or data standards defined in metadata. This paper takes
you through the steps necessary to add a basic metadata report and
discusses patterns for developing metadata report plug-ins.
2:30 p.m.
Accessing and Extracting Data from the Internet Using
Qiaohao Zhu, Alberta Health Services - Cancer Care
Sunita Ghosh, I.ARE.H.
Paper 121-2012
This paper shows you how to use SAS to automatically access web pages
from Internet and extract useful information from the web pages. We first
review some basic elements of Internet accessing, and then review the
accessing and extraction tools provided by Base SAS®. When the SAS tools
are not enough or too complicated to use, we show how you can use
external programs (cURL and Perl/LWP) and integrate the results from
external programs into a SAS data set. Finally, we present four different
examples to illustrate how to use these tools to deal with different levels of
complexity for web accessing and data extraction.
3:00 p.m.
Matching Data Using Sounds-Like Operators and SAS®
Compare Functions
Amanda Roesch, Educational Testing Service
Paper 122-2012
By combining both sounds-like operators and compare functions, SAS can
quickly identify many intended matches between almost any two strings.
First, using the sounds-like (either SOUNDEX or =*) operator, SAS will pair
every match that sounds even relatively close. Yes, this will result in
numerous pairings, but that’s where compare functions are useful. They can
parse the possibilities down for further evaluation. The compare functions
discussed here include COMPARE, COMPGED and CALL COMPCOST,
COMPLEV, and SPEDIS. Finally, using a sort and a well-devised cutoff value,
SAS will give a final list of the most likely matches. This method not only
increases the prospective matches, it uses logic and reason rather than
manipulating the data itself.
3:30 p.m.
Trend Analysis: An Automated Data Quality Approach
for Large Health Administrative Databases
Mahmoud Azimaee, Institute for Clinical Evaluative Sciences
Paper 123-2012
Stability across time is one of the important components in Data Quality
Assurance Process. This paper talks about a SAS® macro that has been
designed to automate testing of stability across time as part of a larger data
quality application package. Outlier analysis has been used for identifying
unusual changes over time within large health administrative databases.
The macro chooses the most appropriate model for smoothing the data
curve/line. Potential outliers will be flagged on the scatterplot as
subspecies points. Results will be presented only in a graphic format to be
included in a Data Quality Report.
4:00 p.m.
A Simple Yet Effective Way to Perform a Variable Cross
Walk Between Multiple Data Sets
Binh Le, Center for Disease Control and Prevention
Huong Pham, Macro International
Paper 124-2012
Analyzing data from multiple complex data sets requires that analysts have
knowledge of each data set’s structure. Comparing variable names, labels,
and formats between more than two complex data sets can be challenging.
A data dictionary and SAS procedures such as PROC COMPARE are
commonly used to complete this task. However, PROC COMPARE only
allows comparison of two data sets at a time. We present relatively simple
procedures that data analysts can use to identify the changes in the
structures of two or more than two data sets which can pinpoint areas in
which existing SAS code need to be modified to account for changes in the
variable names, labels, or formats.
4:30 p.m.
Evolving from Data Management to Master Data
Wilbram Hazejager, SAS
Paper 125-2012
The proliferation of enterprise-level applications (along with the
expectation for shared, synchronized information) drives the need for the
development of a single view of the key data entities in common use across
the organization. Therefore master data management has become one of
the fastest-growing application areas in recent times. This presentation
provides an overview of how DataFlux® qMDM can enhance your data
management initiatives and put you on the path to developing a complete
view of your data.
Data Mining and Text Analytics — Northern
Hemisphere A-3
8:00 a.m.
It’s About Time: Discrete Time Survival Analysis using
SAS® Enterprise Miner™
Sascha Schubert, SAS
Susan Haller, SAS
Taiyeong Lee, SAS
Paper 132-2012
The new survival analysis algorithm in SAS Enterprise Miner 7.1 provides
analysts with an alternate approach to modeling the probability of
customer behavior events. Traditional binary classification approaches
provide a snapshot view of event propensities, while survival analysis can
generate a time based function of event probabilities. This time-based view
can help organizations to optimize their customer strategies by gaining a
more complete picture of customer event likelihoods. This paper briefly
explains the theory of survival analysis and provides an introduction to its
implementation in SAS Enterprise Miner. An example illustrates the usage
of this analytical algorithm using a customer churn data set.
9:00 a.m.
Dickens vs. Hemingway: Text Analysis and Readability
Statistics in Base SAS®
Jessica Hampton, CIGNA
Paper 133-2012
Although SAS® provides a specific product for text mining (SAS® Text
Miner), you may be surprised how much text analysis you can readily
perform using Base SAS. The author introduces the topic with some
background on widely used readability statistics and tests in addition to a
brief comparison of Hemingway and Dickens. After selecting two
appropriate readability tests and texts of similar length, she describes data
preparation challenges, including how to deal with punctuation, case,
common abbreviations, and sentence segmentation. Using a few simple
calculated macro variables, she develops a program which can be reused to
calculate readability tests on any sample input text file. Finally, she validates
her SAS output using published readability statistics from sources such as
Amazon and
9:30 a.m.
Combine Data Sets Using Inexact Character Variables in
Kulwant Rai, Darden Business School, University of Virginia
Paper 134-2012
This project proposes an algorithm to combine data sets using inexact
character variables, and implements this algorithm using SAS software.
When this algorithm is used with PROC SQL, it allows combining datasets
based on several inexact variables, hence producing better matches. This
procedure offers realistic solutions for accurate and more complete
matching of inexact data fields. Apart from being simple and easy to
understand, the strength of this procedure is to condense information from
several inexact character variables into one numerical measure. Thus, many
valid matches can be captured that previously could only be made by an
individual’s exhaustive visual inspection of the datasets. The procedure will
save time and effort for anyone trying to combine datasets with inexact
character variables.
10:00 a.m.
Hands-on Workshops — Southern Hemisphere II
SAS® Since 1976: An Application of Text Mining to
Reveal Trends
Zubair Shaik, Oklahoma State University
Satish Garla, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
8:00 a.m.
Paper 135-2012
Given documents with a time stamp, text mining can identify trends of
different topics in text and how they change over time. We apply text
mining using SAS® Text Miner to discover trends in the usage of SAS® tools
in industries, analyzing 8,429 abstracts published from SAS Users Group
International Conferences and SAS Global Forums since 1976. Results of the
analysis clearly show a varying trend in the representation of industries in
the proceedings from decade to decade. We observed a significant
difference in the association of key concepts related to statistics or
modeling. A SAS macro developed for this research, %SAS1976, can analyze
papers published for any conference, provided the conference papers are
accessible in formats such as .doc, .pdf, .txt, and more.
10:30 a.m.
Correlating the Analysis of Opinionated Texts Using
SAS® Text Analytics with Application of Sabermetrics to
Cricket Statistics
Praveen Lakkaraju, SAS
Saratendu Sethi, SAS
Paper 136-2012
Cricket is a game similar to baseball. It is rich in statistics, and there are
plenty of online discussions about the game and the players. Sabermetrics
deals with using statistical methods to analyze baseball records. This paper
presents the results of experiments with applying Sabermetrics-style
principles to the game of cricket and correlating the findings with analysis
of opinionated text. Examples use various products from the SAS® Text
Analytics suite to demonstrate how structured and unstructured data
analysis can be applied together to gain insights into real-world data.
11:00 a.m.
A New Age of Data Mining in the High-Performance
David Duling, SAS
Wayne Thompson, SAS
Jared Dean, SAS
Paper 137-2012
Today’s businesses are challenged with both analyzing huge data volumes
and improving and accelerating their predictive modeling. SAS® HighPerformance Data Mining technology is based on the SAS® HighPerformance Analytics model for distributed processing alongside the
database to make use of multiple processors and vast sums of memory
across multiple machines. Data mining features cover the full spectrum of
building a predictive model, including data selection, exploratory analysis,
transformations, feature selection, dimension reduction, linear and
nonlinear modeling, and model performance comparison. New SAS HighPerformance Data Mining procedures ease the transition for SAS
programmers. This paper discusses the options and methods available for
use in High-Performance Data Mining and uses real data for performance
Quick Results with ODS Graphics Designer
Sanjay Matange, SAS
Paper 153-2012
You just got the study results and want to get some quick graphical views
of the data before you begin the analysis. Do you need a crash course in SG
Procedures just to get a simple histogram? What to do? The ODS Graphics
Designer is the answer. With ODS Graphics Designer, you can create
histograms, scatter plot matrices, classification panels, and more using an
interactive “drag-and-drop” process. You can render your graphs in batch
with new data, and output the results to any open ODS destination. You
can even view the generated GTL code as a leg up to GTL programming.
You can do all this without cracking the book or breaking a sweat. This
hands-on-workshop takes you step-by-step through the application’s
Hands-on Workshops — Southern Hemisphere I
8:00 a.m.
Queries, Joins, and WHERE Clauses, Oh My!!
Demystifying PROC SQL
Christianna Williams, Independent Consultant
(Invited) Paper 149-2012
Subqueries, inner joins, outer joins, HAVING expressions, set operators…
just the terminology of PROC SQL might intimidate SAS programmers
accustomed to getting the DATA step to do our bidding for data
manipulation. Nonetheless, even DATA step diehards must grudgingly
acknowledge that there are some tasks, such as the many-to-many merge
or the "not-quite-equi-join," requiring Herculean effort to achieve with
DATA steps that SQL can accomplish amazingly concisely, even elegantly.
Through increasingly complex examples, this workshop illustrates each of
PROC SQL’s clauses, with particular focus on problems difficult to solve with
“traditional” SAS code. After all, PROC SQL is part of Base SAS® so, although
you might need to learn a few new keywords to become an SQL wizard, no
special license is required!
10:00 a.m.
An Introduction to Creating Multi-Sheet Microsoft Excel
Workbooks the Easy Way with SAS®
Vince DelGobbo, SAS
Paper 150-2012
Transferring SAS data and analytical results between SAS and Microsoft
Excel can be difficult, especially when SAS is not installed on a Windows
platform. This talk provides basic information on how to use Base SAS® 9
software to create multi-sheet Excel workbooks (for Excel versions 2002 and
later). You learn techniques for quickly and easily creating attractive, multisheet Excel workbooks that contain your SAS output using the ExcelXP
tagset. The techniques that are presented in this talk can be used regardless
of the platform on which SAS software is installed. You can even use them
on a mainframe! More in-depth information on this topic is presented, if
time permits.
Hands-on Workshops — Southern Hemisphere II
Hands-on Workshops — Southern Hemisphere II
10:00 a.m.
3:30 p.m.
Using SAS® ODS Graphics
Chuck Kincaid, Experis Business Analytics
Paul Dorfman, Paul Dorfman Consulting
Lessia Shajenko, Bank of America
(Invited) Paper 154-2012
The SAS ODS Graphics procedures are built upon the Graphics Template
Language (GTL) in order to make the powerful GTL easily available to the
user. PROC SGPLOT and PROC SGPANEL are two of the procedures that can
be used to produce powerful graphics that used to require a lot of work.
This upgrade is similar to the ease-of-use upgrade in output manipulation
when ODS was first published. This presentation will teach the audience
how to use PROC SGPLOT and PROC SGPANEL and the new capabilities
they provide beyond the standard plot. By using these new capabilities, any
user can tell the story better.
1:30 p.m.
How to Perform and Interpret Chi-Square and T-Tests
Jennifer Waller, Georgia Health Sciences University
(Invited) Paper 155-2012
For both statisticians and non-statisticians, knowing what data looks like
before more rigorous analyses is key to understanding what analyses can
and should be performed. After all data have been cleaned up, descriptive
statistics have been calculated and before more rigorous statistical analysis
begins, it is a good idea to perform some basic inferential statistical tests
such as chi-square and t-tests. This workshop concentrates on how to
perform and interpret basic chi-square, and one- and two-sample t-tests.
Additionally, how to plot your data using some of the statistical graphics
options in SAS® 9.2 will be introduced.
Hands-on Workshops — Southern Hemisphere I
1:30 p.m.
SAS® Enterprise Guide® with SAS® On-Demand for
Academics: Everything You Need to Know After "It's
AnnMaria Mars, The Julia Group
(Invited) Paper 156-2012
The DOW loop is a nested, repetitive DATA step structure enabling you to
isolate instructions related to a certain break event before, after, and during
a DO loop cycle in a naturally logical manner. Readily recognizable in its
most ubiquitous form by the DO UNTIL(LAST.ID) construct, which readily
lends itself to control break processing of BY group data, the DOW loop's
nature is more morphologically diverse and generic. In this workshop, the
DOW loop's logic is examined via the power of example to reveal its
aesthetic beauty and pragmatic utility. In some industries like Pharma,
where flagging BY group observations based on in-group conditions is
standard fare, the DOW loop is an ideal vehicle, greatly simplifying the
alignment of business logic and SAS® code.
Hands-on Workshops — Southern Hemisphere I
3:30 p.m.
Doing More with the SAS® Display Manager: From Editor
to ViewTable - Options and Tools You Should Know
Art Carpenter, CA Occidental Consultants
(Invited) Paper 151-2012
If you have used the interactive interface for SAS, you have used the Display
Manager. Because it is functional “right out of the box,” most users do little
to customize the interface. This is a shame, because the Display Manager
contains a great many hidden opportunities to make it even more
powerful, even easier to use, and customized for your way of using the
interface. You think that you know the Display Manager, but you will be
amazed at what you have yet to learn. From simple tricks that will save you
hours of work, to embedding tools and macros in the Enhanced Editor,
there is so very much more that we can do in the Display Manager.
Pharma and Health Care Providers — Oceanic 1
(Invited) Paper 152-2012
8:00 a.m.
SAS On-Demand for Academics is a free "cloud-based" version of SAS®
software available to university faculty, researchers, and students. In this
hands-on workshop, participants will learn the administrative details (how
and where to get it, set up students account, upload files), use SAS
Enterprise Guide to solve both simple and complex statistical problems and
practice troubleshooting some of the more common issues that arise when
using SAS On-Demand for teaching. Because SAS On-Demand is now free
to university researchers as well, participants will also run tasks that were
used for two research projects, a descriptive statistics analysis from survey
data and a survival analysis.
Defining the Development Process and Governance of
Implementing ADaM within an Organization
Chris Decker, d-Wise Technologies, Inc.
(Invited) Paper 172-2012
Over five years ago, the initial release of the CDISC ADaM standard was
more a set of best practices then a standard that could be implemented.
Given the maturity of ADaM ad that time and the lack of any FDA direction,
companies basically avoided the need to implement ADaM – if it’s not
required, I’m not doing it. With the release of the ADaM Implementation
Guide in 2009 and the FDA’s renewed commitment to standards,
companies realize they have to jump on the ADaM bandwagon or get left
behind. This paper presents a hybrid case study describing how standards
governance, ADaM development, and an ADaM implementation plan were
implemented across a variety of pharmaceutical companies to support the
development and use of analysis data standards.
9:00 a.m.
Automatic Consistency Checking of Controlled
Terminology and Value Level Metadata between ADaM
Datasets and Define.xml for FDA Submission
Xiangchen Cui, Vertex Pharmaceuticals, Inc.
Min Chen, Vertex Pharmaceuticals, Inc.
Paper 173-2012
When submitting clinical study data (SDTM and ADaM data sets) in
electronic format to the FDA, it is preferable to submit data definition tables
(define.xml) and a reviewer guide (define.pdf). It is desirable to ensure the
consistency between data sets and define files, and achieve technical
accuracy and operational efficiency. This paper introduces a SAS® macro
approach to automate consistency-checking of controlled terminology and
value level metadata between ADaM data sets and define.xml. It avoids the
waste of time and resources for verification of the consistency and/or
resolution of inconsistency at a later stage. It also details how to develop
ADaM Metadata (programming specification) for automation purpose,
illustrates five scenarios of mismatches from consistency checking, and
provides corresponding resolutions to these mismatches.
to corroborate OpenCDISC messages in order to understand and resolve
compliance issues. Realizing that a validation check generates the same
message, the SAS code that corroborates an issue should be quite similar.
This paper discusses a template SAS program that facilitates the process of
using OpenCDISC for assessing CDISC compliance.
11:00 a.m.
SUPPQUAL—Where's My Mommy?
Sandra Nguyen, PharmaNet/i3
Paper 177-2012
When using CDISC standards, there might be situations in which a field has
been collected on a CRF or included in a vendor data transfer that seems to
be clinically relevant, but is not topic data belonging in a standard or
custom SDTM domain (any of the three general observation classes).
Because nonstandard variables cannot be added to SDTM domains, this
data typically gets mapped to a SUPPQUAL (supplemental qualifiers) data
set. But, what do we do when there is not an obvious parent record
corresponding to this data within one of the SDTM domains? This paper
provides guidelines to use to determine how best to handle these
9:30 a.m.
11:30 a.m.
SAS® Macros to Transpose SDTM Data Sets
Chunmao Wang, National Institutes of Health
Sharing SAS programs between PC, Server and SAS Drug
Magnus Mengelbier, Limelogic Ltd
Paper 174-2012
In pharmaceutical industry, when producing analysis datasets from clinical
data, usually it is necessary to transpose variables for lots of domains.
Individually manipulating each domain data would be time-consuming and
error-prone. However, thanks to CDISC, the data structures are standardized
so that it is possible to use macros to handle SDTM data sets automatically.
Here we present a set of macros to transpose multiple columns for some
domains. It not only saves programmers time but also improves data
10:00 a.m.
Using SAS® Macros to Remediate Existing SDTM Data
Sets for New Drug Application (NDA) Submission
Yanwei Han, Vertex
Paper 175-2012
This paper presents the development of SAS® macros to prepare existing
SDTM data sets for submission with a new drug application (NDA). Within
this process, there was late-stage checking of SDTM data sets and the
creation of a single SAS program to make necessary changes to the SDTM
data sets for every study within the submission.
10:30 a.m.
A Standard SAS® Program for Corroborating Clinical
Data Interchange Standards Consortium Error Messages
John Gerlach, TAKE Solutions, Inc.
Ganesh Thangavel, TAKE SOLUTIONS Inc
Paper 176-2012
The Clinical Data Interchange Standards Consortium (OpenCDISC)
application does a thorough job of assessing the CDISC compliance of
Study Data Tabulation Model (SDTM) domains. However, the error and
warning messages are often rather vague, even cryptic. Thus, it is beneficial
Paper 178-2012
SAS Drug Development has become a common SAS environment within
Life Science organisations, whether large or small. It is not uncommon that
programs are developed outside of SAS Drug Development, either as a
standard process or simply that an external organisation is not allowed
access to the SAS Drug Development environment. The convention to
configure parameters for any SAS program to be executed within SAS Drug
Development provides a logistical exercise in retaining context for projects,
compounds, protocols, reporting event, etc. We discuss a convention and
consider example code that allows for the context to be retained for a SAS
program, whether it resides within SAS Drug Development or executed on
a SAS PC or server.
1:30 p.m.
Automation of Paper-Based Medical Surveys Using the
SAS® BI Platform – Custom Web Forms for Real-Time
Ian Healy, BrightHeight Solutions
Rocket Wong, Maine Medical Center
Paper 179-2012
Maine Medical Center has traditionally relied on paper-based surveying and
inspections in order to determine the level of patient satisfaction and safety
on a regular basis. The ability to generate substantial business intelligence
using paper surveys was both labor-intensive and proved difficult to
convey the results to the hospital community. The Center for Performance
Improvement – BI Competency Center worked to bridge this gap by
developing custom web forms using the SAS BI platform. These forms have
eliminated most paper surveying and resulted in ease of data entry,
instantaneous feedback as well as real-time reporting, and dashboards to
assist in efforts for continuous improvement at Maine Medical Center.
2:00 p.m.
4:00 p.m.
Error Reduction and Report Automation Approaches for
Textually Dense Pharmaceutical Regulatory
Conformance Incident Data
Barry deVille, SAS
Mark Wolff, SAS
Physician Practice Pattern Variation: Using Data Mining
and Predictive Modeling to Identify and Control Costly
Treatment Patterns
David Ogden, SAS
Paper 180-2012
Paper 183-2012
The Periodic Safety Update Report (PSUR) is a significant feature of the
post-trial, in-market monitoring of drug efficacy. The manufacturer’s
response to a drug-use incident is comprehensive: new literature must be
searched; a wide range of interactions with other agents must be
examined; and, finally, a complete clearance must be claimed. This
response is a huge information-processing burden due to the many factors
at play and because so much of the information (starting with the original
exception report, including numerical data) is delivered in unstructured
textual format. This presentation discusses a proof of concept carried out
on behalf of a major pharmaceutical manufacturer that deployed a variety
of text content identification and manipulation techniques to eliminate
manual error and automate the report production.
Health insurance providers want to control the ever-increasing cost of
healthcare, while ensuring quality outcomes. Learn how SAS® Enterprise
Guide® and SAS® Enterprise Miner™ can be used to identify which
physicians are generating excessive costs and which practice patterns are
leading to cost reduction opportunities. This analysis of Physician Practice
Pattern Variation focuses on an automated “layered” reporting method for
producing actionable results, with automated output to Microsoft Excel
and/or Microsoft Word. The challenge is to devise an approach to model
the expected costs associated with treating a given condition (e.g., upperrespiratory infections). This discussion covers the three main areas of such a
project: standardized data preparations, explanatory modeling, and
information delivery (highlighting an approach to turning analytical output
into actionable information).
3:00 p.m.
5:00 p.m.
Cluster Mapping of Medicare Severity Diagnosis-Related
Groups for ICD-10 Conversions
Keith Jones, Humana Lifesynch
Clustering Physicians Based on Professional Proximity
Using SAS®
Niam Yaraghi, State University of New York (SUNY at Buffalo)
Anna du, State University of New York (SUNY at Buffalo)
Raj Sharman, State University of New York (SUNY at Buffalo)
Ram Gopal, University of Connecticut
Ramaswamy Ramesh, State University of New York (SUNY at
Ranjit Singh, State University of New York (SUNY at Buffalo)
Paper 181-2012
Diagnostic-Related Groups (DRG’s) have been critical to Medicare
procedure-based billing for prospective payment and risk management
since it was first implemented. More recently Medicare Severity-DRG’s
weigh top factors to optimize cost, time, and clinical outcomes. Now
Medicare prescribes Generalized Equivalence Map (GEM) clusters to convert
ICD-9 to ICD-10 by 2013 to optimize all billing in the future. Such cluster
maps can be used by providers and insurers to optimize their clinical
outcomes and costs using SAS/STAT® procedures and SAS® Enterprise
Miner™, with reporting process automation by SAS® Enterprise Guide®, and
visualization using SAS/GRAPH® with JMP®, to build and monitor diagnosis
and procedure cost classification models. Examples are presented to
support scaled SAS® ®solutions to comply with, and benefit from, these new
Medicare guidelines.
3:30 p.m.
SAS® Solutions Make HEDIS Measures Programming
Qingfeng Liang, UPMC Health Plan, Inc.
Paper 182-2012
The Healthcare Effectiveness Data and Information Set (HEDIS), a product of
the National Committee for Quality Assurance (NCQA), is one of the most
widely used sets of health-care performance measures, which are related to
many significant public health issues such as cancer, cardiovascular
conditions, diabetes, depression, etc. For health-care managed care
organizations (MCOs), HEDIS presents interesting information systems and
programming challenges to MCOs because of the complication of
insurance claims and the complexity of the measures. The advantages of
SAS® programming power and its solutions make these challenges much
easier to overcome. This paper explains the challenges that we faced when
we were trying to tackle these measures. More importantly, this paper
discusses the powerful SAS solutions that helped us overcome these
Paper 184-2012
We show how SAS can be used to conduct a network analysis of physicians
in order to identify the professional proximity of different specialties based
on the common patients flow. The professional proximities can be used as a
basis for further research in various topics such as adoption and usage
patterns of Healthcare Information Exchange systems. We are building this
paper on the previous paper (Zheng, 2011). In the current paper, we
provide clearer codes and present the results based on real data, and we
further expand the previous paper by showing the differences in MultiDimensional Scaling (MDS) analysis results when the number of dimensions
increase. Moreover, we show how the outputs of MDS analysis can be used
to conduct a cluster analysis.
Planning and Support — Northern Hemisphere
1:30 p.m.
Managing SAS® Technical Support in a Research
Michael Raithel, Westat
(Invited) Paper 185-2012
Westat uses SAS software as a core capability for providing government
and private industry clients with analysis and characterization of their data.
Staff programmers, analysts, and statisticians use SAS to manage, store, and
analyze client data as well as to produce tabulations, reports, graphs, and
summary statistics. Because SAS is so widely used at Westat, the
organization has built a comprehensive infrastructure to manage SAS
technical support issues. This paper provides an overview of Westat’s SAS
technical support infrastructure, which provides a central resource that
handles SAS software issues so that the programming and statistical staff
can concentrate on providing clients with cutting-edge analysis.
2:30 p.m.
After Analytics, What’s Next?
Ping Koo, Singapore Management University
Murphy Choy, School of Information System
Paper 186-2012
After gathering great insights from our data, the next steps would be
devising and executing the strategy based on these insights. Strategy
planning and execution can be seen as both an art and a science. Without
proper planning and execution, these insights that we gathered would be
meaningless. Many frameworks have been devised to help businesses in
their strategy planning and execution. But most of them have generally
been used at corporate level; for instance Balanced Scorecards. Here we
introduce a framework, adapted from an ancient treatise of war, “Sun Zi Art
of War,” that can provide a strong framework at the strategy planning and
execution stage so that analysts can assess the feasibility of their devised
4:00 p.m.
Community Discovery: Best Tips and Features from
Communities on SAS®
Renee Harper, SAS
Cynthia Zender, SAS
Paper 189-2012
Not long ago, "community" meant a collection of neighborhoods, grocery
stores, and a place to gather and talk about life. Then, it all changed to
include a gathering place on <gasp> the Internet. SAS recently upgraded
our discussion forums to a new community format, making it easier for you
to stay informed, share knowledge, grow your professional network, and
get help. But how do you go about posting a question online? One key to
successful community interaction is to learn how to ask your question
rather than posting a riddle. We'll cover the basic netiquette of posting to
the new community (or to any online forum). Come prepared for interactive
and hands-on learning.
5:00 p.m.
Tales from the Help Desk 5: Yet More Solutions for
Common SAS® Mistakes
Bruce Gilsen, Federal Reserve Board
3:00 p.m.
Paper 190-2012
Successfully On-Boarding SAS® Analysts
Aaron Augustine, SymphonyIRI Group
This paper reviews common mistakes and shows how to fix them. The
following topics are reviewed. 1. Use comments in a macro. 2. Handle
missing values: arithmetic calculations versus functions. 3. Use %SYSFUNC
to execute DATA step functions in a macro. 4. Use the macro IN operator to
check in a macro if a value equals one of the values in a list. In the context of
reviewing these mistakes, the paper provides details about SAS system
processing that can help users employ SAS more effectively. This paper is
the fifth of its type; see the references for four previous papers that review
other common mistakes.
Paper 187-2012
Finding and successfully on-boarding SAS Analysts can be challenging.
Each new hire can have varying levels of work and SAS experience. As such,
an On-Boarding process needs to be flexible to account for these situations
while covering the necessary information to incorporate new hires into a
company. This paper serves to outline a profile used for hiring SAS analysts
and the training plan after they are hired. It was written for working in a
research and development group within a CPG industry, but the structure
could be applied to most new-hire situations. This paper is most applicable
to Base SAS® and SAS/STAT® and could be applied to any operating
3:30 p.m.
What Is a SAS® Mentor and Why Do I Need One?
Stanley Fogleman, Harvard Clinical Research Institute
Paper 188-2012
A SAS mentor can be a valuable resource to junior programmers just
starting out, or programmers who may have used other high-level
languages and are just starting to use SAS. The paper will focus on
preparing a plan for a hypothetical junior programmer, with the goal of
becoming a more proficient programmer over a one- or two-year period.
SAS, unlike some other languages, does not lend itself to being self-taught
and some things that might look like an obvious choice can actually lead to
performance penalties. The most important thing that mentors can provide
is guidance – for things worth studying more and things that might be
interesting, but you might use only infrequently.
Programming: Beyond the Basics — Asia 5
8:00 a.m.
Executing a PROC from a DATA Step
Jason Secosky, SAS
Paper 227-2012
All programs are built by creatively piecing together simpler parts into a
larger whole. In SAS®, the SAS macro facility provides an ability to group
and piece together analytic blocks. However, writing complex programs
using the SAS macro facility can be difficult and cumbersome. An easier
way is to combine two new functions, RUN_MACRO and DOSUB, with DATA
step code. RUN_MACRO and DOSUB enable DATA step code to
immediately execute a macro and act on the result, something that was not
possible before SAS® 9.2. This paper presents examples of using these two
new functions from DATA step to code programs that are easier to read,
write, and maintain.
9:00 a.m.
Is Your Failed Macro Due to Misjudged “Timing”?
Arthur Li, City of Hope/University of Southern California
(Invited) Paper 228-2012
The SAS® macro facility, which includes macro variables and macro
programs, is the most useful tool to develop your own applications.
Beginning SAS programmers often don’t realize that the most important
function in learning a macro program is understanding the macro language
processing rather than just learning the syntax. The lack of understanding
includes how SAS statements are transferred from the input stack to the
macro processor and the DATA step compiler, what role the macro
processor plays during this process, and when best to use the interface to
interact with the macro facility during the DATA step execution. In this talk,
these issues are addressed by creating simple macro applications step-bystep.
10:00 a.m.
What Do You Mean, Not Everyone Is Like Me: Writing
Programs for Others to Run
Jack Hamilton, Kaiser Foundation Health Plan
(Invited) Paper 229-2012
Writing programs that other people will run can be difficult, and programs
that might be run on multiple operating systems and versions of SAS® can
be even more difficult. And if you're like me, a program you wrote a year
ago might as well have been written by someone else. This presentation
discusses some of the challenges of writing programs to be run by others,
and some possible guidelines to get around those challenges - some based
on beyond-the basics programming, some based on programming style.
Some of the topics that will be discussed are: DOW loops, hash objects,
regular expressions, choosing system options, and minimizing log
11:00 a.m.
Macro Coding Tips and Tricks to Avoid "PEBCAK" Errors
Matthew Karafa, Cleveland Clinic Foundation
(Invited) Paper 230-2012
No matter how well you document what a macro’s parameters are
supposed to accept, at least one user will ignore your hard work and try
something unanticipated. This presentation describes my parameterchecking scheme, which provides such users direct feedback via the SAS®
log. This feedback looks like a standard SAS error message, and it gives
meaningful explanations of what went wrong. Thus, it should prevent the
macro author from having a long debugging session, only to conclude that
the user passed the macro inappropriate information. Also included are
several debugging tips and tricks I use and some information about library
level macros and autocall libraries. This presentation should be applicable
to both beginning and advanced macro coders.
1:30 p.m.
Solve the SAS® ODS Data Trap in PROC MEANS
Peter Crawford, Crawford Software Consultancy Limited
Myra Oltsik, Acorda Therapeutics
Paper 231-2012
The first version of this solution to the ODS Trap in PROC MEANS was
presented at SUGI-31(2006). This update presents a revised version of the
macro supporting additional features and eliminating a surprising error.
Those who wish a practical solution to this ODS Data Trap will appreciate
the enhancements that correct and simplify usage. Policies and impact of
the macro will be described for the more advanced audience who are
interested in adapting the macro and its techniques for their own purposes.
2:00 p.m.
Getting to the Good Part of Data Analysis: Data Access,
Manipulation, and Customization Using JMP®
Audrey Ventura, SAS
Paper 232-2012
Effective data analysis requires easy access to your data no matter what
format it comes in. JMP can handle a wide variety of formats. Once the data
is in JMP, you can choose from a variety of options to reshape the data with
just a few clicks. Finally, customize your data with labels, colors, and data
roles so that graphs and charts automatically look the way you want them
to. This paper walks through two or three story lines that demonstrate how
JMP can easily import, reshape, and customize data (even large datasets) in
ways that allow your data to be displayed in vibrant visualizations that will
wow your audience.
3:00 p.m.
Seamless Reporting Automation through the
Integration of JMP®, SAS®, and VBA
Rachel Poulsen, TiVo
Raghunathan Chakravarthy, TiVo Inc
Paper 233-2012
The TiVo user interface (UI) is continuously enhanced for design. To monitor
and improve UI performance, statistical tests are run on multiple test cases
across various dimensions, and weekly reports are generated. The reports
require the flexibility of Excel, the analysis power of JMP® and SAS®, and the
reporting convenience of PowerPoint. This can be accomplished by
integrating JMP, SAS® ODS, and Excel VBA to create an automation tool that
seamlessly runs the analyses, conditionally formats the table output, and
generates reports in PowerPoint. JMP automates the statistical analysis, SAS
ODS calls Excel VBA macros for the conditional formatting of Excel data
sets, and SAS ODS generates reports in PowerPoint. This paper discusses
the tasks involved in the process flow of the automation tool.
3:30 p.m.
SG Techniques: Telling the Story Even Better!
Chuck Kincaid, Experis Business Analytics
Jack Fuller, Experis
(Invited) Paper 234-2012
The SAS® Statistical Graphics (SG) procedures, SGPLOT, SGPANEL,
SGSCATTER, and SGRENDER, are exciting additions in SAS® 9.2 that give
easy access to some of the power of the Graphics Template Language
(GTL). As good as these procedures are in helping you tell your analytical
story (and they are good), there are techniques that can add extra value to
your graphs. This paper discusses four concepts, level ordering, slicing,
banking, and stacking, introduced by William S. Cleveland in his book
"Visualizing Data." For these techniques, we explain the concepts, provide
examples, and outline the basic algorithms in this paper. The audience for
this presentation is the statistician or business analyst who wants to tell
their story even better.
4:30 p.m.
10:00 a.m.
Comparison of SAS® Graphic Alternatives, Old and New
LeRoy Bessler, Bessler Consulting and Research
A Tutorial on the SAS® Macro Language
John Cohen, Advanced Data Concepts
(Invited) Paper 235-2012
Since my first encounter with SAS/GRAPH® software in 1981, I have tried to
create communication-effective SAS graphics, rather than simply accept
the defaults. This tutorial shows alternative customized SAS graphic
solutions, using both the traditional G procedures and the new SG
(Statistical Graphics) procedures. It covers graphs written to disk to later be
inserted into Microsoft PowerPoint, Word, or Excel, or simply printed, but
also demonstrates the benefits of Web-enabled SAS graphs, as well as Webenabled SAS graphs linked forward and backward with an Excel
spreadsheet of the data graphed. A graph enables quick and easy inference,
but the actual data assures correct inference. A spreadsheet of data can be
post-processed however your information recipient wishes, using a tool
available and familiar to almost anyone.
Programming: Foundations and Fundamentals —
Asia 4
8:00 a.m.
Moving Data and Results Between SAS® and Microsoft
Harry Droogendyk, Stratia Consulting Inc.
(Invited) Paper 247-2012
Microsoft Excel spreadsheets are often the format of choice for our users,
both when supplying data to our processes and as a preferred means for
receiving processing results and data. SAS offers a number of means to
import Excel data quickly and efficiently. There are equally flexible methods
to move data and results from SAS to Excel. This paper will outline the many
techniques available and identify useful tips for moving data and results
between SAS and Excel efficiently and painlessly.
9:00 a.m.
Why Does SAS® Say That? What Common DATA Step and
Macro Messages Are Trying to Tell You
Charles Mullin, SAS
Kevin Russell, SAS
Paper 248-2012
SAS notes, warnings, and errors are written to the log to help SAS
programmers understand what SAS is expecting to find. Some messages
are for information, some signal potential problems, some require you to
make changes in your SAS code, and some might seem obscure. This paper
explores some of these notes, warnings, and errors that come from DATA
step and macro programs. This paper deciphers them into easily
understood explanations that enable you to answer many of your
(Invited) Paper 249-2012
The SAS macro language is another language layering on top of regular SAS
code. Used properly, it can make programming easier and more fun. While
not every program is improved by using macros–adding another syntax to
learn and additional debugging challenges – we gain using macros as code
generators, saving repetitive and tedious effort, for passing parameters to
avoid hard coding, and to pass code fragments, thereby making certain
tasks easier than using regular SAS alone. Macros facilitate conditional
execution and can be used as program modules—standardized and reuseable throughout your organization. We will examine macros and macro
variables, statements, and functions. We will introduce interaction between
macros and regular SAS language, offer tips on debugging, and the SAS
macro options.
11:00 a.m.
Where’s the LISTING Window? Using the New Results
Viewer in SAS® 9.3
Cynthia Zender, SAS
Paper 250-2012
Are you making the transition from earlier versions of SAS to SAS® 9.3? Did
you wonder what happened to the LISTING window? Do you like the new
cumulative HTML file, but wish you could figure out how to get different
behavior for selected pieces of output? This paper outlines several
techniques for adjusting the behavior of the SAS windowing environment
Results Viewer using version 9.3 of SAS. Along the way, you also see
examples of the new ODS-related options that allow you to establish
destination and style defaults in your configuration file. By the time this
presentation is over, you will understand how to work with the new Results
Viewer behavior. Several job aids are provided that outline the alternatives.
1:30 p.m.
Exploring DATA Step Merges and PROC SQL Joins
Kirk Lafler, Software Intelligence Corporation
(Invited) Paper 251-2012
Explore the various DATA step merge and PROC SQL join processes. This
presentation examines the similarities and differences between each, and
provides examples of effective coding techniques. Attendees examine the
objectives and principles behind merging and joining, as well as the coding
constructs associated with inner and outer merges and joins, and hash
2:30 p.m.
Selecting All Observations When Any Observation Is of
Christopher Bost, MDRC
Paper 252-2012
A data set might contain multiple observations per person. Suppose you
want to keep all observations for a person if at least one observation for
that person meets certain criteria. This paper shows how to use PROC SQL
to select all observations when any observation is of interest. The first
method uses a subquery; the second method uses the GROUP BY and
HAVING clauses. The SQL techniques are compared and contrasted with a
traditional DATA step match-merge.
3:00 p.m.
Import and Output XML Files with SAS®
Yi Zhao, Merck & Co., Inc.
Paper 253-2012
XML files are widely used in transporting data from different operating
systems or data storages. Processing XML files efficiently becomes one of
the necessary technical skills for a SAS programmer. This paper presents
four aspects of importing and exporting XML files with SAS: (1). Using XML
engine LIBNAME and the DATA step to import or output data between XML
and SAS data sets. (2). Using PROC COPY. (3). Developing XMLMap to
facilitate the conversion; and (4). Importing XML file to Microsoft Excel and
converting it to a SAS data set. Sample program codes and tips are
provided and discussed.
3:30 p.m.
Write Once, Run Anywhere! How to Make Your SAS®
Application Speak Many Languages
Mickael Bouedo, SAS
Paper 254-2012
Do you have SAS users worldwide? Do you want your SAS application to be
useable in many languages? New SAS® 9.3 internationalization features will
get you there efficiently. If you want to offer your SAS application in two,
four, or ten languages, SAS internationalization features help you write your
code once so it can run in many languages. Internationalization is the step
which generalizes your product to be language independent. Localization
is the second step and adapts the product to meet the needs of different
languages and cultures. This paper describes how to successfully
internationalize your SAS programs and make them ready for the world.
4:30 p.m.
BIG Money PROC TABULATE—Generating Great Reports
with the TABULATE Procedure
Ben Cochran, The Bedford Group
(Invited) Paper 256-2012
Several years ago, one of my clients was in the business of selling reports to
hospitals. He used PROC TABULATE to generate part of these reports. He
loved the way this procedure crunched the numbers, but not the way the
final reports looked. He said he would go broke if he had to sell naked PROC
TABULATE output. So, he wrote his own routine to take TABULATE output
and render it through Crystal Reports. That was before SAS® came out with
the ODS. Once he got his hands on ODS, he kissed Crystal Reports goodbye. This paper is all about using PROC TABULATE to generate fantastic BIG
Money reports.
Reporting and Information Visualization —
Southern Hemisphere IV
8:00 a.m.
Off the Beaten Path: Create Unusual Graphs with ODS
Prashant Hebbar, SAS
Paper 267-2012
You open the latest edition of Time magazine and see a unique spiral bar
chart of revenue shortfall by state, or your coworker sends you a link to an
interesting population pyramid graph on a Web site and you ask yourself:
“Can I do that using SAS®”? Often, as it is for these two graphs, the answer is
“Yes.” With a little bit of data transformation and some creativity, you can
generate spiral plots, radar plots, and population pyramids using ODS
Graphics, without a shred of annotate code. This presentation covers many
tricks and tips to create unique graphs that grab the reader’s attention, and
also deliver the information effectively. Learn how to stretch the
boundaries of what is possible with ODS Graphics.
9:00 a.m.
Creating the Perfect Plot with PROCs EXPAND and
SGPLOT: The Dynamic Duo of Time Series Display
Andrew Karp, Sierra Information Services
(Invited) Paper 268-2012
SAS® users often face critical challenges when tasked to prepare and display
a series of values ordered in the time domain. For example, values may be
missing from the series, or the observed data needs to be either aggregated
(for example, “rolled upfrom daily observations to quarterly values) or
interpolated (weekly estimates derived from monthly observations). Or, a
“moving time window statistic” requires computation and display.
Attending this presentation equips you with an understanding of how to
apply the wide range of time series preparation capabilities of PROC
EXPAND, and then how to use the powerful PROC SGPLOT resources to
create the graphics images you need to “tell the story” contained in the
data values to others.
10:00 a.m.
Sparklines in the DATA Step Graphics Interface from
Murphy Choy, School of Information System
Paper 269-2012
Sparklines is one of the latest visualization techniques that analysts are
using to assist them in visualizing information. An invention by the famous
visualization expert Edward Tufte, sparklines incorporates many of his key
ideas in the use of charts and diagrams to reinforce certain concepts and
ideas. Sparklines can be implemented in SAS in certain ways. In this paper,
we illustrate the ease of creating sparklines using the DATA Step Graphics
Interface (DSGI) techniques from SAS/GRAPH®.
10:30 a.m.
Mix and Match: Diversity in Displaying Data
Melissa Hill, Yale University
Julie Kezik, Yale University
Paper 270-2012
A programmer is often asked to “run some frequencies” or “put together a
quick report” in order to share results with a group. Just as every scientist
has a preferred output style (graph, table, figure, list, etc.) every
programmer has a preferred way of getting there. The results of posing this
question to five colleagues produced a variety of approaches including the
well as visualization techniques in JMP®.
11:00 a.m.
Essential SAS® ODS PDF
Patrick Thornton, SRI International
Paper 271-2012
This paper lists and demonstrates the ODS techniques that I have found
most useful in creating user-friendly PDF reports in SAS® 9.2 on a Windows
operating system. ODS techniques include creating PDF files (e.g., ODS PDF
FILE= STYLE= KEYWORD= COLUMNS=), modifying page setup (e.g.,
orientation, date, title, and footnote), and saving procedural output to data
sets (e.g., ODS OUTPUT). The examples also demonstrate simultaneously
creating two PDF destinations (i.e., ODS PDF ID=) and selectively including
or excluding procedural output to each destination (e.g., ODS PDF SELECT,
EXCLUDE and WHERE=). Two PDF files are simultaneously created where
PROC FREQ listings are directed to one file and selected PROC FREQ results
are combined with PROC REPORT to create an executive summary in the
other PDF file.
11:30 a.m.
The Graph Template Language: Beyond the SAS/GRAPH®
Jesse Pratt, Cincinnati Children's Hospital
Paper 285-2012
The SGPLOT and SGPANEL procedures are powerful tools that are capable
of producing many types of high-quality graphs; however, these
procedures have some limitations. What happens when one is asked to
specifically produce a graph that these procedures cannot create? The
Graph Template Language (GTL) is much more flexible when it comes to
creating customized displays. This paper presents situations where the
SGPLOT and SGPANEL procedures break down, then briefly introduces GTL,
and finally uses the GTL to generate the displays not possible in PROC
1:30 p.m.
ODS Document from Scratch
Kevin Smith, SAS
Paper 273-2012
ODS Document is most likely the most under-utilized feature of ODS. ODS
Document gives you the ability to customize the structure of your reports in
ways that no other ODS features can. It enables you to store the actual ODS
objects created when running a report which you can then later rerun
without invoking the procedures from the original report. You aren't limited
to simply regenerating the same report; you can change the order in which
objects are rendered, the table of contents, the templates used, macro
variables, and ODS and system options. Even if you don't consider yourself
an ODS wizard, don't be afraid to take a peek at the features of ODS
Document in this paper because we'll be taking it from scratch.
2:30 p.m.
SAS/FSP® Provides the Best Customizable Form Viewer
Peter Crawford, Crawford Software Consultancy Limited
(Invited) Paper 274-2012
Drilling through data to examine exceptions (outliers or missing), you want
to see a lot of detail about one row. You need a "form viewer". SAS/FSP
demonstrates, perhaps the best.There are aspects to SAS/FSP that are not
matched among the related products; i.e., SAS/AF®, ViewTable, SAS® Web
Report Studio, nor the downloadable extension for SAS® Enterprise Guide®
software that promises an FSEDIT screen.The feature least supported
(IMHO) among these alternatives is the customizable Form Viewer of
FSBROWSE. After "what" and "how", this paper will show how customizing
is easily re-usable in the explorer of SAS Display Manager. Although it may
be “off-strategy” as SAS/FSP will work in neither SAS Enterprise Guide nor
SAS Portal, this paper shows the benefits of having a simple customizable
3:30 p.m.
Let the Data Paint the Picture: Data-Driven, Interactive,
and Animated Visualizations Using SAS®, Java and the
Processing Graphics Library
Johnston Hall, North Carolina State University
Ryan Snyder, Institute for Advanced Analytics
Paper 275-2012
This paper introduces a scalable technique that combines the data
manipulation capabilities of Base SAS® 9.2 with the Java Processing
graphics library to generate customizable visualizations. With an instructive
example, the reader is guided through connecting to the sashelp.iris
sample data using a SAS/SHARE® server to build a visualization applet. The
explanation includes details for adding animation and simple mouse and
keyboard interactions into the visualization. A basic understanding of
Object Oriented (OO) programming is assumed. The included example was
designed for the Windows platform; however, Java and Processing are
designed to support many other operating systems. Additional reference
material and sample visualizations are also included.
4:00 p.m.
Multisheet Workbooks Using the ODS Excelxp Tagset
Cynthia Stetz, Bank Of America Merrill Lynch
Paper 276-2012
Most of us are engaged in providing data to information consumers at least
some of the time, and by far the most often requested format is the Excel
workbook. Fortunately, we can rely on SAS® to supply us with innovative
tools to make this task easier. One of those tools that I have recently started
using to great effect is the ODS Excelxp tagset. By harnessing some of the
vast capabilities available within this tagset, in concert with the judicious
application of macro code and DDE, I am now able to deliver nicely
formatted, multisheet native Excel workbooks for any number of subsets of
my data as might be desired.
4:30 p.m.
Proficiency in JMP® Advanced Visualization
Charles Shipp, Consider Consulting, Inc.
Kirk Lafler, Software Intelligence Corporation
Paper 277-2012
The premier tool for robust statistical graphics is JMP. It combines easy
navigation, advanced algorithms, and graphical output you can trust. After
a brief introduction of JMP navigation and resources within the JMP
software, we take a tour of classical and modern advanced graphical
capability of JMP. We then introduce case studies that show the power of
JMP, ending with graphics and analysis. To conclude, we cover directions in
training and JMP user exchange.
5:00 p.m.
Hyperslicing with SAS®
Jonathon Khoo, Singapore Management University
Ping Koo, Singapore Management University
is right for an organization. This paper will explain some of the central
concepts behind cloud computing and cover scenarios where SAS is
executed within a cloud infrastructure along with the issues involved.
Finally, it will identify some of the business drivers that may lead an
organization towards a cloud deployment.
10:00 a.m.
The New SAS® Programming Language: DS2
Jason Secosky, SAS
Paper 397-2012
DS2 is being designed for data manipulation and data modeling
applications. DS2 also enhances a SAS programmer’s repertoire with objectbased tools by providing data abstraction using packages and methods.
DS2 executes both within a SAS session by using PROC DS2, and within
selected databases where the SAS® Embedded Process is installed. This
session introduces the basic objectives of DS2 and where it is currently
being used and opens the discussion on future directions for this new
Paper 278-2012
11:00 a.m.
Hyperslice is one of the newer techniques in visualization that involves the
viewing of high dimensional data in a simple visualization. The data is
centered around a chosen point based on a certain dimension, creating a
slice. The user can further explore this data through manipulating this
chosen point. However, as SAS does not provide this type of interactivity
directly, in this paper, we explore some possible ways to implement this
extreme slicing of data and exploration of the information using the same
concepts proposed in Hyperslice within different aspects of SAS.
Decision Management, Speed, and Agility
Ryan Schmiedl, SAS
Michael Ames, SAS
Wayne Thompson, SAS
SAS® Futures — Americas Seminar Room
8:00 a.m.
Empowering SAS® Enterprise Application with
Collaboration and Search
Murali Nori, SAS
Paper 395-2012
Decision management systems are not passive; rather, they adapt to the
needs of an organization, providing the agility needed to address everchanging business circumstances. They close the loop between the
backroom model building and integration with front room business
decisions. They are the key to integration of predictive analytics into
operational systems. In this session, we’ll present the vision of the future of
SAS® integrated decision management suite covering discovery, business
rules, batch and real-time execution, as well as an integration of an
enterprise service bus.
Paper 391-2012
SAS® Futures — Asia 1
In Organizations, people collaborate and make decisions collectively. SAS
analytical and Business Intelligence provide the data, analysis, and answers
to the business questions. But the interpretation and decisions are made
with the right people at the right time with the right context. SAS
Collaboration strategy facilitate the creation of private groups and
discussions that will help share SAS content and come together to make
good decisions, faster. Customers can expect to have Social experience like
Facebook in the context of SAS applications and SAS BI. Come and hear
how SAS plans to push the boundaries beyond simple search and help
customers explore and discover trends, scenarios, information, seamlessly.
1:30 p.m.
9:00 a.m.
A Sunny Outlook for Cloud Computing with SAS®
Craig Rubendall, SAS
Robert Stephens, SAS
Paper 390-2012
Cloud computing (which can include other topologies such as Virtualization
and Platform as a Service): What does that mean? Who would want to use
it? How might it change the way that SAS delivers and users run SAS
products? These are important questions, the answers of which must be
understood before the decision can be made of whether cloud computing
The Future of SAS® Deployment: From MSI Packages to
Web-Based Control
Mark Schneider, SAS
Paper 394-2012
Take a glimpse into the not-so-distant future of installing and configuring
SAS software. We’ll describe, and in some cases demonstrate, short-term
enhancements to SAS® 9.3 functionality, including MSI and RPM
provisioning, automatic hot-fix download and deployment, and console/
linemode for the SAS® Download Manager, SAS® Deployment Wizard, and
SAS® Deployment Manager. We’ll also outline longer-term initiatives like
Web-based orchestration of multi-machine deployments and support for
“hot” maintenance, applied without shutting down your SAS environment.
2:30 p.m.
User-Assisted Modeling: How SAS® Text Analytics Will
Help You Pinpoint Data of Interest
James Cox, SAS
Saratendu Sethi, SAS
Richard Foley, SAS
Paper 396-2012
Have you ever wanted to discover information, where the criterion is “I’ll
know it when I see it”? This summer’s release of SAS® Text Miner, SAS®
Sentiment Analysis, and SAS® Content Categorization will provide active
learning capabilities, a collaborative process between the user and the
system. With the interactive approach provided by active learning, the user
is able to discover and understand topics and concepts hidden within a
collection of documents.
3:30 p.m.
High-Performance Statistical Modeling
Robert Cohen, SAS
Robert Rodriguez, SAS
Paper 393-2012
The explosive growth of data, coupled with the emergence of powerful
distributed computing platforms, is driving the need for high-performance
statistical modeling software. After an overview of this landscape, you will
see a demonstration of new modeling procedures in SAS® HighPerformance Analytics software. These procedures tame the massive tasks
of fitting predictive models by exploiting all the cores in distributed
computing environments. The demonstration will set the stage for a
discussion of ongoing development to extend this family of procedures.
Finally, the discussion will turn to future directions for high-performance
statistical modeling.
4:30 p.m.
Capitalizing on SAS® and Hadoop
David Shamlin, SAS
Howard Plemmons, SAS
Nancy Rausch, SAS
Rick Langston, SAS
Michael Ames, SAS
Paper 392-2012
An overview of SAS integration with Hadoop. Unlike traditional databases,
Hadoop scales to address the needs of large-scale data-intensive
distributed applications in a reliable, cost-effective manner. In this session,
we’ll present examples and use cases highlighting connectivity with SAS/
ACCESS®, introduce a new Base® SAS procedure and file interface
extensions specifically for Hadoop. Finally, we’ll provide a sneak peek into
the future of embedding SAS processing within Hadoop.
SAS® Enterprise Guide® Implementation and
Usage — Northern Hemisphere E-4
8:00 a.m.
Using SAS® Enterprise Guide® to Coax Your Excel Data
Into SAS®
Mira Shapiro, Analytic Designers LLC
Kirk Lafler, Software Intelligence Corporation
Paper 289-2012
Importing Microsoft Excel files into SAS can often be a challenge. Perfectly
formatted Excel files with labels in the first row and idiosyncrasy-free, clean
data is not usually the norm. We will show how to overcome many of the
obstacles associated with creating SAS data sets from Excel workbooks by
using various combinations of SAS Enterprise Guide 4.3's features. The
import wizard, generated code, code suggestion mechanism, options, and
the ability to preview the first section of a CSV file will all be shown as
mechanisms for creating analytic data sets from Excel input.
8:30 a.m.
Converting Complex Microsoft Access Database
Reporting Systems Using SAS® Enterprise Guide®
Scott Milbuta, University of Central Florida
Paper 290-2012
The need to store more and more data related to aggregate enrollment
information for use in the Registrar’s Office at the University of Central
Florida led to the development of several Access databases several years
ago to assist in capturing this data. The Access databases were expanded
and adapted to perform additional functions beyond their intended scope.
Due to the amount of data stored and the delivery methods originally
implemented they were no longer able to meet the organization’s
reporting needs effectively and a new solution was required. This paper will
explore the transition from existing silo data stores to the SAS® Business
Intelligence environment and how it was accomplished using SAS
Enterprise Guide and SAS® Stored Processes on the SAS Information Portal.
9:00 a.m.
The Alarm Effect of Statistical Process Control Process in
Automotives Manufacturing
Ying Wang, Shanghai General Motor
(Invited) Paper 293-2012
Statistical Process Control (SPC) is the application of statistical methods to
the monitoring and control of a process to ensure that it operates at its full
potential to produce conforming product. Under SPC, a process behaves
predictably to produce as much conforming product as possible with the
least possible waste. While SPC has been applied most frequently to
controlling manufacturing lines, it applies equally well to any process with a
measurable output. Key tools in SPC are control charts, a focus on
continuous improvement, and designed experiments. With SAS® Enterprise
Guide®, the SPC method can be carried out conveniently.
10:00 a.m.
2:30 p.m.
Finding Your Inner Query with SAS® Enterprise Guide®
Michael Burke, SAS
I-kong Fu, SAS
Using SAS® Enterprise Guide® As a Powerful Regulating
Guangzhi Zhang, CBRC
Xing Guo, CBRC
SAS Enterprise Guide 5.1 introduces the concept of reusable, query-based
templates. SAS Enterprise Guide users have been able to create task-based
templates to save custom settings for some time now. Query-based
templates offer the ability to perform a similar role for the SAS Enterprise
Guide Query Builder, allowing speedy access to previously designed
queries which might have included time-consuming work spent fashioning
the perfect table join, computed column, or filter. SAS Enterprise Guide 5.1
also allows you to reuse certain types of query-based templates as
subqueries in computed columns and filters. This paper describes how
query-based templates work and how to use them to answer special
problems by turning them into subqueries in the point-and-click Query
Builder environment.
(Invited) Paper 295-2012
Paper 292-2012
11:00 a.m.
Up Close and Personal with SAS® Enterprise Guide® 5.1
Anand Chitale, SAS
Lina Clover, SAS
Paper 302-2012
SAS Enterprise Guide continues its evolution bringing great new
capabilities and enhancing usability and end user productivity. These
capabilities range from enhanced capabilities for SAS® programmers, new
data exploration capabilities with enhanced descriptive statistics, highly
visual and interactive multidimensional data analysis, and enhanced query
and analysis to achieve increased performance. This paper brings you up
close and personal with the key highlights of SAS Enterprise Guide 5.1,
demonstrating the application of these capabilities helping you learn how
to get more from your data in less time than ever before.
1:30 p.m.
Take a Fresh Look at SAS® Enterprise Guide®: From
Point-and-Click Ad Hocs to Robust Enterprise Solutions
Christopher Schacherer, Clinical Data Management Systems,
Paper 294-2012
Early versions of SAS Enterprise Guide met with lukewarm acceptance
among many SAS® programmers. As SAS Enterprise Guide has matured, it
has proven to be a powerful tool not only for end users less familiar with
SAS programming constructs, but also for experienced SAS programmers
performing complex ad hoc analyses and building enterprise-class
solutions. Still, many experienced SAS programmers fail to add SAS
Enterprise Guide to their SAS toolkit. They face the barriers of an unfamiliar
interface, new nomenclature, and uncertainty that the benefits of using SAS
Enterprise Guide outweigh the time spent mastering it. Especially for this
group (but also for analysts new to SAS), the present work provides an
orientation to the SAS Enterprise Guide interface and nomenclature.
The ability to manipulate and analyze data from different banks in an
effective manner is a big challenge for a banking regulator. The purpose of
this paper is to introduce how SAS Enterprise Guide and a powerful SAS
Enterprise Guide indicator calculation plug-in can help regulators to meet
their complex regulating requirements especially data import from
different databases and complex indicator calculation. With some
customization efforts from SAS® consultants, SAS Enterprise Guide becomes
a powerful regulating analysis weapon. It meets our ever-changing
regulating analysis requirements no matter how data is structured and how
we need to manipulate it. This paper provides a detailed introduction on
how we import data and define indicators through SAS Enterprise Guide in
an innovative way.
3:30 p.m.
Case Study: Implementing and Administering SAS®
Enterprise Guide® across the Enterprise as a Solution for
Data Access Security
Linda Sullivan, University of Central Florida
Ulf Borjesson, University of Central Florida
Evangeline Collado, University of Central Florida
Maureen Murray, University of Central Florida
Paper 296-2012
This paper presents a case study detailing why and how the SAS® Enterprise
Guide® client was chosen, approved by UCF’s security office, and rolled out
to selected power users and unit IT shops in the university community as
the solution to replace two distinct data access and reporting tools. The
selection increased the number of SAS Enterprise Guide users across the
university by a factor of five.
4:00 p.m.
Best Practices for Administering SAS® Enterprise Guide®
Casey Smith, SAS
Paper 297-2012
Customers and clients just want it to work. Management wants it to be
secure and “intuitive” while sliding you a list of ten new unrelated “action
items” needed, “when you aren’t busy”. You are in the middle, the grease
between the cogs. When your phone rings, it isn’t going to be someone
gushing about how smooth everything is running. Sound familiar? If part of
your work is administering and supporting people using SAS Enterprise
Guide, then don’t miss this talk. We cover deployment issues, environment
customization, handling libraries, roles, SAS® Grid Manager support,
migration, and project maintenance. Come in and learn about the SAS
Enterprise Guide tools designed to make administrative life just a bit easier.
SAS® Workshop Series — Asia 2
8:00 a.m.
SAS® Workshop: Creating SAS® Stored Processes
Eric Rossland, SAS
Paper 404-2012
This workshop provides hands-on experience creating SAS Stored
Processes. Workshop participants will:
• use SAS® Enterprise Guide® to access and analyze data
• create stored processes which can be shared across the organization
• access the new stored process from the SAS® Add-In for Microsoft Office
• create reports
• use the SAS add-in Quick Start Tools
2:30 p.m.
SAS® Workshop: DataFlux® Data Management Studio
Kari Richardson, SAS
Paper 409-2012
This workshop provides hands-on experience using DataFlux Data
Management Studio to profile and then cleanse data. Workshop
participants will:
• learn to navigate DataFlux Data Management Studio
9:00 a.m.
SAS® Workshop: SAS® Data Integration Basics
Kari Richardson, SAS
Paper 405-2012
This workshop provides hands-on experience using SAS® Data Integration
Studio to construct tables for a data warehouse. Workshop participants will:
• define and run a data profile
• define and run a data job
3:30 p.m.
SAS® Workshop: SAS® Platform Administration
Christine Vitron, SAS
• define and access source data
Paper 410-2012
• define and load target data
This workshop provides hands-on experience using SAS® Management
Console to administer the platform for SAS® Business Analytics. Workshop
participants will:
• work with basic data cleansing
10:00 a.m.
• back up the metadata
SAS® Workshop: SAS® Enterprise Guide® 5.1
Eric Rossland, SAS
• manage access to application features with roles
Paper 406-2012
This workshop provides hands-on experience using SAS Enterprise Guide.
Workshop participants will:
• access different types of data
• analyze data using the Data Explorer
• create reports and analyses
• register a user in the metadata
4:30 p.m.
SAS® Workshop: Creating SAS® Stored Processes
Eric Rossland, SAS
Paper 411-2012
This workshop provides hands-on experience creating SAS Stored
Processes. Workshop participants will:
11:00 a.m.
• use SAS® Enterprise Guide® to access and analyze data
SAS® Workshop: SAS® Data Integration Advanced
Kari Richardson, SAS
• access the new stored process from the SAS® Add-In for Microsoft Office
• create stored processes which can be shared across the organization
Paper 407-2012
This workshop provides hands-on experience using SAS® Data Integration
Studio to take advantage of the Loop transformations. Workshop
participants will:
• define and load a control table
• parameterize an existing job
• create an iterative job using the control table and parameterized job
1:30 p.m.
SAS® Workshop: SAS® Add-In for Microsoft Office 5.1
Eric Rossland, SAS
Paper 408-2012
This workshop provides hands-on experience using the SAS Add-In for
Microsoft Office. Workshop participants will:
• access and analyze data
Social Media and Networking — Northern
Hemisphere A-1
8:00 a.m.
SAS Social Media or How I Learned to Love the Blog
Christopher Battiston, Hospital for Sick Children
Paper 303-2012
Being a newcomer to SAS®, I was struggling with finding information
specifically related to Canadian health-care data analysis. I spent a few days
roaming through Google and stumbled across the Toronto Area SAS
Society, which took me to the SAS Canada Community, which is a site
dedicated to SAS users in the northern half of North America. It was here
that I met some great people, learned a lot, and realized that social media is
not the evil, privacy-breaching monster I thought it was. This presentation
is an attempt to get others to see the benefits of sites like the SAS Canada
8:30 a.m.
Topic Discovery, Tracking, and Characterization of Social
Media Conversations for Point of Origin and
Dissemination Discovery
Barry deVille, SAS
Gurpreet Bawa, SAS
Paper 304-2012
Social media conversations cover a wide range of human experience often
in novel, sometimes revolutionary ways. The words that are used to express
content might reflect mundane events or might sometimes reflect radical
new ways of thinking and behavior. The correct identification of
conversation in real time is essential in order to effectively respond or
intervene in a timely fashion. This presentation demonstrates the
interdependency between vocabulary use and social networks that is
critical to understanding conversations in social media channels, where
they came from, where they are going, and what impact they are likely to
have. We show how topics are extracted from social media and how they
are identified and tracked. Examples of the language use, social networks,
and associated impacts are demonstrated.
macro (%GetTweet) to collect and summarize tweets and then an
application of sentiment analysis on the fetched tweets using SAS Text
Miner using directed search and summarization of specific text items.
10:30 a.m.
Social Media and Networking: The Ins and Outs
Todd Case, Biogenidec
Paper 307-2012
With companies being bought, sold, and eliminated, it's critical to build a
name and a reputation for what specific skills you bring to your specific
SAS® community. Social media is a powerful way to present your
contributions to employers as follows: getting your name and skills out
there for potential employers and recruiters, controlling the presentation of
your experience, recommending others and having them recommend you,
understanding the relationships among employees within an industry, and
networking and getting back in touch with programmers. This paper
discusses these and other topics related to social media, with the intent
being on using social media methods that can help you find the right
candidate (from a manager’s perspective) or a job (from a candidate’s
9:30 a.m.
11:00 a.m.
Connect with SAS® Professionals around the World with
LinkedIn and
Charles Shipp, Consider Consulting, Inc.
Kirk Lafler, Software Intelligence Corporation
Using Facebook to Engage SAS® Users
Ping Koo, Singapore Management University
Murphy Choy, School of Information System
Paper 305-2012
(Invited) Paper 308-2012
Accelerate your career and professional development with LinkedIn and Establish and manage a professional network of trusted
contacts, colleagues and experts. These social networking and collaborative
communities enable users to connect with millions of SAS users worldwide,
anytime, anywhere. This presentation explores how to maximize LinkedIn
profiles and social networking content, develop a professional network of
friends and colleagues, join special-interest groups, access a Wiki-based
web site where anyone can add or change content on pages of the web
site, share biographical information between both communities using a
built-in widget, exchange ideas in Bloggers Corner, view scheduled and
unscheduled events, use a built-in search facility to search for wiki-content,
collaborate on projects and file sharing, read and respond to specific forum
topics, and more.
Social media has become a regular and common platform for organizations
and businesses to engage relevant stakeholders. This is a very surprising
phenomenon given that social media has taken its current form within the
past few years. Because it is a new technology,” there is no proper literature
on how social media should be used to achieve designated objectives. As
such, the use of social media is by trial and error, gaining lessons from the
usage experience. Here we would like to share our experiences in using
Facebook to engage members of the Singapore SAS Users Group (SUG). We
have not reached a stage where we are considered successful, but we hope
that such sharing can help other SUGs around the world.
10:00 a.m.
Analyzing Sentiments in Tweets about Wal-Mart’s
Gender Discrimination Lawsuit Verdict Using SAS® Text
Hari Hara Sudhan Duraidhayalu, Oklahoma State University
Satish Garla, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
Paper 306-2012
Social Media has gained considerable attention as a valuable source to
monitor customers and public reactions following corporate events.
Especially the Tweets posted on Twitter are often used to spot trends,
moods, and sentiments of customers and public. Given the huge volume of
tweets that gets posted every day, it is extremely difficult for firms to spot
current trends related to the public’s expressed sentiments about activities
of the firm in the tweets. This paper demonstrates the application of a SAS®
1:30 p.m.
Twitter and Facebook Analysis: It’s Not Just for
Marketing Anymore
Jodi Blomberg, SAS
Paper 309-2012
Think marketers have a hard time analyzing social media? Law enforcement
has it even tougher. Crimes are being discussed all over Twitter and
Facebook, and nobody’s tagging them #crime. A vast multitude of other
topics are also being discussed in these venues, making capturing
intelligence from all of this text no simple task. We address two social media
analytics applications for law enforcement. First, we show how to search
Facebook for a specific set of people, gather up the publicly available data
and present it in a digestible form for the analyst. Second, we show how
tracking events on Twitter can help us understand precursors to activity at
events, such as riots. This is useful to anyone using SAS® to analyze social
2:30 p.m.
Social Media Panel
Stephanie Thompson, Independent Consultant
(Invited) Paper 310-2012
How can SAS® professionals use, consume, and create social media content
effectively? This panel of both SAS and SAS users will discuss it all with time
for questions.
Statistics and Data Analysis — Northern
Hemisphere E-2
8:00 a.m.
Tips and Strategies for Mixed Modeling with SAS/STAT®
Kathleen Kiernan, SAS
Jill Tao, SAS
Phil Gibbs, SAS
Paper 332-2012
Inherently, mixed modeling with SAS/STAT procedures, such as GLIMMIX,
MIXED, and NLMIXED, is computationally intensive. Therefore, considerable
memory and CPU time can be required. As a result, the default algorithms
in these procedures might fail to converge for some data sets and models.
This paper provides recommendations for circumventing memory
problems and reducing execution times for your mixed modeling analyses.
This paper also shows how the new HPMIXED procedure can be beneficial
for certain situations, as with large sparse mixed models. Lastly, the
discussion focuses on the best way to interpret and address common notes,
warnings, and error messages that can occur with mixed models.
Statistics and Data Analysis — Northern
Hemisphere E-1
8:00 a.m.
Inflated Beta Regression: Zero, One, and Everything in
Christopher Swearingen, UAMS Dept of Pediatrics
Maria Melguizo, University of Arkansas for Medical Sciences
Zoran Bursac, University of Arkansas for Medical Sciences
(Invited) Paper 325-2012
Beta Regression, an extension of generalized linear models, can estimate
the effect of explanatory variables on data falling within the (0,1) interval.
Recent developments in Beta Regression theory extend the support interval
to now include 0 and 1. The %Beta_Regression macro is updated to now
allow for Zero-One Inflated Beta Regression.
Statistics and Data Analysis — Northern
Hemisphere E-2
9:00 a.m.
The Steps to Follow in a Multiple Regression Analysis
Theresa Ngo, Kelley Blue Book
Paper 333-2012
Multiple regression analysis is the most powerful tool that is widely used,
but also is one of the most abused statistical techniques. There are
assumptions that need to be satisfied, statistical tests to determine the
goodness fit of the data and accuracy of the model, potential problems that
may occur in the model, and difficulties of interpreting the results. The first
challenge is in the application of the techniques – how well analysts can
apply the techniques to formulate appropriate statistical models that are
useful to solve real problems. The second challenge is how to use a suitable
statistical software package – such as SAS® – to deploy the correct
procedures and produce the necessary output for assessing and validating
the postulated model.
Statistics and Data Analysis — Northern
Hemisphere E-1
9:00 a.m.
Are You in Need of Validation? Psychometric Evaluation
of Questionnaires Using SAS®
Eric Elkin, ICON Clinical Research
(Invited) Paper 426-2012
Presentations at prior SAS user group meetings have focused on factor
analysis and related topics in order to develop the scale structure of a
questionnaire. Instead, this presentation will assume that the scale has
already been developed but needs validation as a new scale or for use in a
new population. The examples are taken from health-related quality-of-life
research and will follow the “Guidance for Industry” published by the FDA
(Dec. 2009). The focus will be on the classical test theory approach to
psychometric validation including internal consistency, test-retest, and
inter-rater reliability; construct and known-groups validity; and
responsiveness. The discussion will include samples of SAS code as well as
tips for interpreting and presenting results.
Statistics and Data Analysis — Northern
Hemisphere E-2
9:30 a.m.
Transforming Variables for Normality and Linearity:
When, How, Why, and Why Nots
Steven LaLonde, Rochester Institute of Technology
Paper 430-2012
Power transformations are often suggested as a means to "normalize"
univariate data which may be skewed left or right, or as a way to "straighten
out" a bivariate curvilinear relationship in a regression model. This talk will
focus on identifying when transformations are appropriate and how to
choose the proper transformations using SAS® and new features of the
ODS. There is also a discussion of why, or why not, you may choose the
"optimal" transformation identified by SAS.
Statistics and Data Analysis — Northern
Hemisphere E-1
Statistics and Data Analysis — Northern
Hemisphere E-1
10:00 a.m.
11:00 a.m.
Making Exploration of Nonlinear Models Fast and Easy
Using JMP® 10
Don McCormack, SAS
Speeding Up Discovery
John Sall, SAS
Paper 326-2012
Nonlinear models are frequently encountered in applied technological
areas such as the semiconductor and pharmaceutical industries. Defect
density and pharmacokinetic models are two examples where fitting a
straight line to data is inadequate or inappropriate. Exploration of these
models is often tedious and time consuming, and model comparison is
difficult. Through its nonlinear platform, JMP 10 introduces a quick and
simple way to fit multiple curves and explore competing models,
streamlining the discovery process. Two detailed examples are given using
data similar to that found in practice.
Paper 327-2012
With fast hardware and multithreaded software, interactive exploration
becomes feasible in larger problems. But that also means that it will take
some resourceful techniques, combined with human judgment, to look
across thousands of variables, to find the relationships that are worth
looking at.
Statistics and Data Analysis — Northern
Hemisphere E-2
11:00 a.m.
Statistics and Data Analysis — Northern
Hemisphere E-2
10:00 a.m.
Standardized Difference: An Index to Measure the Effect
Size between Two Groups
Dongsheng Yang, Cleveland Clinic
Paper 335-2012
Standardized difference (STD) is an efficient index to measure the effect size
between two groups. Unlike t-tests or other statistical significance tests,
STD is independent of sample size. Thus, it is increasingly used to compare
baseline covariates in clinical trials and propensity score matched studies.
Besides using standard formulas to calculate standardized differences for
normal distributed continuous variables or binary variables, some
researchers have recommended a nonparametric method to get
standardized differences for skewed data. Meanwhile, the modified
Mahalanobis distance method is recommended for categorical variables
that have more than two levels. Finally, a SAS® macro has been developed
to calculate the standardized difference without using the PROC IML.
10:30 a.m.
A Generalized Approach to Estimating Sample Sizes
Wuchen Zhao, University of Southern California
Arthur Li, City of Hope/University of Southern California
Paper 336-2012
Determining sample size is one critical and important procedure for
designing an experiment. The sample size for most statistical models can be
easily calculated by using the POWER procedure. However, the PROC
POWER cannot be used for a complicated statistical model. This paper
reviews a more generalized method to estimate the sample size through a
simulation approach by using SAS® software. The simulation approach not
only applies to the simple but also to a more complex statistical design.
Introduction to Predictive Modeling with Examples
David Dickey, North Carolina State University
(Invited) Paper 337-2012
This is an introductory paper on models used for prediction. The focus is on
some of the most commonly used techniques, and the paper is intended
for an audience of diverse backgrounds. Through a collection of examples,
the features of the techniques, their implementation in SAS, and things to
watch out for are covered. Basic assumptions are presented in a userfriendly way and hints on how to tell if those assumptions are met, as well
as what to do when they are not met, are covered. The paper’s emphases
are on how to interpret the results and how to distinguish between
important and less important results.
Statistics and Data Analysis — Northern
Hemisphere E-1
1:30 p.m.
Introducing the FMM Procedure for Finite Mixture
David Kessler, SAS
Allen McDowell, SAS
Paper 328-2012
You’ve collected the data and performed a preliminary analysis with a linear
regression. But the residuals have several modes, and transformations don’t
help. You need a different approach, and that calls for the FMM procedure.
PROC FMM fits finite mixture models, which enable you to describe your
data with mixtures of different distributions so you can account for
underlying heterogeneity and address overdispersion. PROC FMM offers a
wide selection of continuous and discrete distributions, and it provides
automated model selection to help you choose the number of
components. Bayesian techniques are also available for many analyses. This
paper provides an overview of the capabilities of the FMM procedure and
illustrates them with applications drawn from a variety of fields.
Statistics and Data Analysis — Northern
Hemisphere E-2
acute myocardial infarction in the Nationwide Inpatient Sample of the
Healthcare Utilization Project. A suite of SAS• procedures is used in analyses,
specifically the procedures LIFEREG, MCMC, NLMIXED, FMM and SEVERITY
1:30 p.m.
Weighted Portmanteau Tests Revisited: Detecting
Heteroscedasticity, Fitting Nonlinear and Multivariate
Time Series
Thomas Fisher, University of Missouri-Kansas City
(Invited) Paper 338-2012
In the 2011 SAS® Global Forum, two weighted portmanteau tests were
introduced for goodness-of-fit of an Autoregressive-Moving average
(ARMA) time series process. This result is summarized and extended for use
as a diagnostic tool in detecting nonlinear and variance-changing
processes such as the Generalized Autoregressive Conditional
Heteroscedasticity process. The efficacy of the weighting scheme is shown
in simulation experiments and analysis of stock market data. The statistics
are easy to implement in SAS® and source code is provided. Lastly, the
versatility of this methodology is discussed for a fitted GARCH, Vector
ARMA, and other time series processes.
2:30 p.m.
Analyzing the Time Series of U.S. E-Commerce Using
Anders Milhøj, University of Copenhagen
Paper 339-2012
In this paper, PROC UCM is applied in an analysis of the series of ECommerce which is published by the U.S. Census Bureau. This rather new
procedure decomposes a time series into intuitive components such as
levels, trends and seasonality which are easily specified in the SAS® code.
The advantages of PROC UCM as an easy-to-use alternative to a careful
econometric analysis will be of focus in the presentation. The results are
mainly presented by the graphical output which adds to the attractiveness
of the procedure. Also, more advanced features of PROC UCM will be
applied such as a discussion of how the seasonality have changed and
various ways to include the total retail sales as an independent variable in
the model.
Statistics and Data Analysis — Northern
Hemisphere E-1
2:30 p.m.
Modeling Heavy-Tailed Distributions in Healthcare
Utilization by Parametric and Bayesian Methods
Joseph Gardiner, Michigan State University
(Invited) Paper 418-2012
Distributions of healthcare utilization such as hospital length of stay and
inpatient cost are generally right skewed. Extreme observations on patients
might be due to severity of illness and medical interventions that have long
in-stays and incur large costs. In this context we demonstrate the
application of several parametric models for fitting heavy tailed data.
Maximum likelihood and Bayesian methods are used to estimate Coxian
phase-type models, mixtures of exponential distributions, and for
comparison the log-logistic and Burr distributions. We illustrate our
methods with an empirical example on fitting models to hospital stays for
Statistics and Data Analysis — Northern
Hemisphere E-2
3:00 p.m.
Variable Selection for Multivariate Cointegrated Time
Series Prediction with PROC VARCLUS in SAS® Enterprise
Miner™ 7.1
Akkarapol Sa-Ngasoongsong, Oklahoma State University
Satish Bukkapatnam, Oklahoma State University
Paper 340-2012
Vector Error Correction Model (VECM) has recently become a popular tool
for economic analysis and forecasting for multivariate co-integrated time
series. However, one problem of this type of model is overparameterization issue. Traditional method to address this problem is to
impose weak exogeneity assumption on variables. Assuming unknown
structural relationship among variables, imposing this assumption alone
may not be sufficient, especially in the case of a large number of
hypothesized variables. This paper presents a variable selection method for
multivariate co-integrated time series prediction using variable clustering
procedure (PROC VARCLUS) in SAS Enterprise Miner 7.1.
3:30 p.m.
Combined Forecasts: What to Do When One Model Isn't
Good Enough
Ed Blair, SAS
Michael Leonard, SAS
Bruce Elsheimer, SAS
Paper 341-2012
SAS® High-Performance Forecasting 4.1 offers a new, innovative process for
automatically combining forecasts. Forecast combination, also called
ensemble forecasting, is the subject of many academic papers in statistical
and forecasting journals; it is a known technique for improving forecast
accuracy and reducing variability of the resulting forecasts. By integrating
these methods into a single software system, SAS High-Performance
Forecasting 4.1 surpasses the functionality of any existing software system
that incorporates this capability. This paper describes this new capability
and includes examples that demonstrate the use and benefits of this new
forecast combination process.
Statistics and Data Analysis — Northern
Hemisphere E-1
3:30 p.m.
Dynamically Evolving Systems: Cluster Analysis Using
David Corliss, Marketing Associates
Paper 329-2012
Cluster analysis, often referred to as segmentation in business contexts, is
used to identify and describe subgroups of individuals with common
characteristics that distinguish them from the rest the population. Although
segments are often identified using static characteristics, evolving systems
might be better described by how things change over time. A medical
patient might be classified by the amount of time since an important event
such as a diagnosis, economic activity might be segmented by stages in an
economic cycle, and neighborhoods might be grouped by stages in
generational evolution. An important success is in astrostatistics, where a
supernova is classified by this technique. Examples are given in biostatistics,
meteorology, econometrics, and astrostatistics.
4:00 p.m.
Exploring the Dimensionality of Large-Scale
Standardized Educational Assessments Using PROC
Jonathan Steinberg, Educational Testing Service
Paper 330-2012
Standardized educational assessments test students in specific subject
areas or measure certain core competencies. Educational researchers
regularly use exploratory factor analysis (EFA) to understand a test’s internal
structure related to its design. PROC PRINCOMP may be used; yet, it has
limitations in dealing with the potentially complex structure of
standardized test data. This paper will demonstrate how PROC FACTOR is
more useful in two ways. First, chi-square hypothesis tests can determine
whether a specified number of factors fit the data, particularly when no a
priori hypotheses exist about the test’s internal structure. Secondly,
rotation of multiple factors can be employed to account for inherent interfactor correlations. This paper is intended for those with good knowledge
of multivariate statistics and moderate levels of SAS® programming
Statistics and Data Analysis — Northern
Hemisphere E-2
4:30 p.m.
Let Oil and Gas Talk to You: Predicting Production
Keith Holdaway, SAS
Paper 342-2012
How do historical production data relate a story about the subsurface oil
and gas reservoirs? Business analysts must perform accurate analysis of
reservoir behavior using only rate and pressure data as a function of time.
This paper introduces methodologies to forecast oil and gas production by
exploring implementations of the AUTOREG, ESM, and MODEL procedures
in SAS/ETS®. The AUTOREG procedure estimates linear regression models
when the errors are autocorrelated. The ESM procedure generates forecasts
by using exponential smoothing models. Examples of the MODEL
procedure arising in subsurface production data analysis are discussed. In
addressing these examples, techniques for pattern recognition,
implementing TREE, CLUSTER, and DISTANCE procedures in SAS/STAT® are
highlighted to explicate the importance of oil- and gas-well profiling to
characterize the reservoir.
Statistics and Data Analysis — Northern
Hemisphere E-1
4:30 p.m.
Exploratory Factor Analysis with the World Values
Diana Suhr, University of Northern Colorado
(Invited) Paper 331-2012
Exploratory factor analysis (EFA) investigates the possible underlying factor
structure (dimensions) of a set of interrelated variables without imposing a
preconceived structure on the outcome (Child, 1990). The World Values
Survey (WVS) measures changes in what people want out of life and what
they believe. WVS helps a worldwide network of social scientists study
changing values and their impact on social and political life. This
presentation will explore dimensions of selected WVS items using
exploratory factor analysis techniques with SAS® PROC FACTOR. EFA
guidelines and SAS code will be illustrated as well as a discussion of results.
Systems Architecture and Administration —
Northern Hemisphere E-3
8:00 a.m.
Guidelines for Preparing Your Computer Systems for
Margaret Crevar, SAS
Tony Brown, SAS
Paper 363-2012
Have you ever wondered if you are really prepared to start the installation
process of SAS software on your hardware? Perhaps you have read the
System Requirements sheets for your SAS release and version, and the
appropriate SAS platform administration guide for your operating system.
Are there other crucial items to consider before the installation process that
are targeted toward your company’s expected performance of SAS? This
paper discusses important hardware environmental areas that need to be
reviewed and addressed; from operating system kernel changes and file
system layouts, to storage array considerations. Even prior to software
installation, proper environment scaling, setup, and tuning are crucial to
optimize the performance of your SAS system.
9:00 a.m.
Customizing SAS® OQ to Provide Business Specific
Testing of SAS Installations and Updates
Steve Huggins, Amadeus Software Limited
Paper 372-2012
The SAS Installation Qualification and Operational Qualification tools
provide a generic inbuilt method of validating a SAS installation. This paper
describes a simple method that allows the Operational Qualification tool to
be customized to execute additional SAS code in order to provide a robust
method for regression-testing a new SAS installation using businessspecific SAS programs. The process involves selecting one or more
indicative SAS programs, benchmarking the expected results, and then
integrating the SAS programs into the Operational Qualification tool. This
paper is aimed at SAS users and administrators wishing to upgrade or
update their SAS installation whilst comprehensively ensuring the
consistency of their results.
9:30 a.m.
11:30 a.m.
Simple Version Control of SAS Programs and SAS Data
Magnus Mengelbier, Limelogic Ltd
Practice on the SAS® Scalable Performance Data Server
Configuration for Maximum Performance
Danni Luo, Prime Therapeutics
David Bianchi, Prime Therapeutics
Stephen Bogacz, Prime Therapeutics
Greg Dorfner, Prime Therapeutics
Paper 365-2012
SAS data sets and programs that reside on a local network are most often
stored using a simple file system with no version control, no audit trail of
changes, and none of the benefits. In this presentation, we show you how
to capitalize on the capabilities of Subversion and other simple,
straightforward conventions to provide version control and an audit trail for
SAS data sets, standard macro libraries, and programs without changing
the SAS environment. Extending the interaction with Subversion using a
standard SAS macro is also explored.
10:00 a.m.
Logging 101: Leveraging the SAS® 9.3 Enhanced
Logging Facility
Margaret Crevar, SAS
Paper 366-2012
Logging and auditing are two of the most important aspects of security for
administrators. SAS 9.3 contains an enhanced logging facility that provides
the ability to finely tune SAS logging and auditing behavior. Applications
such as the SAS® Management Console provide administrators with the
ability to dynamically change logging levels and view log output. SAS
programmers can take advantage of logging features using SAS 4GL
language statements. This paper presents an overview of the enhanced
logging facility and presents SAS 9.3 enhancements.
11:00 a.m.
A Hitchhiker's Guide for Performance Assessment and
Benchmarking SAS® Applications
Viraj Kumbhakarna, Cognizant Technology Solutions, Pvt. Ltd.
Anurag Katare, Cognizant Technology Solutions, Pvt. Ltd.
Paper 367-2012
The paper discusses a stepwise approach to conduct a performance
assessment and a performance benchmarking exercise required to assess
the current state of the IT infrastructure (constituting the hardware and
software) prior to an upgrade. It considers the following steps to be
followed in order to proceed with a planned approach to implement
process improvement: 1) Phase I: Assessment & Requirements gathering a)
Understand ASIS process b) Assess AIX UNIX server configuration 2) Phase
II: Performance assessment and benchmarking a) Server performance i)
Server Utilization ii) Memory Utilization iii) Disk Utilization iv) Network traffic
v) Resource Utilization b) Process Performance i) CPU Usage ii) Memory
usage iii) Disc space 3) Phase III: Interpretation of results for performance
Paper 368-2012
To ensure that the SAS® data warehouse environment was architected to
meet the needs of the volume increases anticipated in the coming years,
and to support the daily activities of analytical-oriented exploring,
querying, data mining, and reporting, we rebuilt the SAS data warehouse in
2010 and 2011. For this project, we constructed six SAS® Scalable
Performance Data (SPD) Server environments (named Dev, QA, UAT, PROD,
DR, and BI). We designed new file systems in each of them. We tuned SPD
Server parameters, conducted performance tests, and completed data
migration. The way that we configured SPD Server can significantly affect
your performance. This paper describes our practice on the production SPD
Server configuration and demonstrates our test results in optimizing
1:30 p.m.
Leveraging an Upgrade to Improve Metadata
Brent Whitesel, Highmark Inc.
Angela Hall, SAS
Paper 369-2012
Upgrading to new hardware gives SAS administrators the rare opportunity
to reorganize and clean up the SAS folders metadata structure. For
Highmark, partial promotion techniques were key to restructuring the
metadata into a more secure and usable structure. This paper details the
partial promotion process and the design considerations used to ensure
that the reorganization maintained all the dependencies between objects.
2:00 p.m.
RTM and SASGSUB, the Power to Know… What Your
Grid Is Doing
Erwan Granger, SAS
Paper 370-2012
Since the third maintenance release of SAS® Grid Manager 9.2, two new
applications are changing the way that you interact with your SAS grid.
Platform RTM for SAS® gives you a graphical user interface to manage your
grid, as well as monitor its activity and performance. SASGSUB brings you
the ability to submit a SAS program to the grid using only the command
line. Individually, each tool brings a whole new set of capabilities to the
grid; together, they allow you to test your grid configuration and validate
its performance, so that you can maximize your investment in SAS Grid
Manager technology and proactively manage your grid environment.
3:00 p.m.
How to Administer a 9,000-User Community on a
Multiple SAS® Metadata Environment
Frank Baars, SNS REAAL
Edwin Nijsen, SNS REAAL
Paper 371-2012
Growing from a relative simple SAS® 9.1.3 BI, SAS® Data Integration Studio
environment with 5 metadata servers and up to 600 users to a complex
structure of in total 13 metadata servers and potentially 9,000 users our
user administration activities needed a serious update.As user
administration was still done by hand, a new automated approach on user
administration was essential. This paper proposes an automated user
administration solution including single sign-on facilities and role-based
access for a multiple SAS platform environment.
3:30 p.m.
Serving SAS®: A Visual Guide to SAS® Servers
Gregory Nelson, ThotWave Technologies, LLC
Paper 364-2012
SAS® has been running on servers since the late 1960s. Despite the
emergence of PCs and workstation-class machines, SAS still reigns supreme
on the server. With the introduction of the SAS platform, the number and
types of servers have grown exponentially. As any good student of the
DATA step will attest, knowing what SAS is doing is a critically important
step in debugging and authoring efficient programs. In this presentation,
we provide a visual tour of SAS. We cover what SAS is doing, how it works,
which server is doing what, when the operating system plays a role, how
security functions, and what happens to your data through this entire
4:00 p.m.
The Top Five Migration Considerations for Success
Andrew Mott, SAS
Paper 373-2012
There are different ways to move a house; you can empty the contents of
your house into a truck and transport your belongings to a new house. Or,
put your house with all its belongings on the back of a truck and relocate
the house. Many people have performed the former, and some the latter;
everyone has a different experience but a similar set of considerations. The
same is true of migrating a SAS® environment. There is a large number of
SAS users who have migrated to SAS® 9.2, and some to SAS® 9.3, so there is
a wealth of experience upon which to draw. This paper reviews a number of
customer experiences to compile the top five considerations for a
successful migration.
5:00 p.m.
Using Dynamic Views as a Supplement to SAS® Security
to Enhance Multiple Levels of Access Requirements to
Row-Level Data Upon SAS Server Startup
Christopher Bresson, Travelers
Marty Flis, SAS
Paper 374-2012
Many industries are challenged with regulatory requirements and customer
demand for database access within the corporate environment. There must
be restrictions in place to protect personal information and limit its access.
This paper shows a supplement to SAS security to allow for row-level access
to sensitive data and restrict access based upon dynamic views driven by
data sets at the time of auto-execution as well as group settings in SAS®
Management Console. This supplement works well with user prompts in
SAS® Stored Processes and SAS® Enterprise Guide®. The code has been
tested in SAS® 9.1.3 and SAS® 9.2 and on Windows and UNIX operating
systems. Benefits include transparency to users and using dynamic views
capable of handling multiple users with different access requirements.
Walt Disney World Swan and Dolphin Resort
Andrew T. Kuligowski, Conference Chair
If you missed key presentations, would like to revisit
some of these presentations, were unable to attend
the conference, or would like to share knowledge
from some popular papers with your colleagues, then
you don’t want to miss SAS Global Forum Take-Out!
Back for a third year due to popular demand, SAS
users are offered a selection of video and audio
presentations via the Internet. This collection of
presentations delivered by presenters at this year’s
conference will be something that users will surely
want to “take home” after the conference. For more
information visit
Applied Business Intelligence — Northern
Hemisphere A-4
8:00 a.m.
SAS® and Greenplum: The Answer to Agile in the Era of
Big Data
Annika Jimenez, Greenplum
Stephen Mooney, GreenPlum
(Invited) Paper 425-2012
Quickly analyzing large amounts of data to get answers that drive timesensitive business decisions is a competitive differentiator and requires a
"modern" IT infrastructure that supports a highly agile analytic processes.
The powerful combination of SAS analytics with Greenplum’s UAP stack is
proven to reduce "Big Analytics" problems to seconds or minutes from
hours or days, enabling the development and management of more
accurate and predictive models and in turn a more responsive organization.
Annika Jimenez, Senior Director of Analytics, and Stephen Mooney, Senior
Data Scientist, will demonstrate the power of SAS and Greenplum to
perform analytical exploration and development on all of an organization's
data to complement their regular analytic operations, in turn achieving
higher model-scoring performance and faster time to results.
9:00 a.m.
Excelling with Excel
Tim Beese, SAS
Greg Granger, SAS
Paper 036-2012
Microsoft Excel is the most widely used tool for data analysis, and it is the
default entry point for many consumers wanting to explore and analyze
data. While Excel is well-suited for basic analysis, it does not provide the
powerful analytics available in SAS®. With the SAS® Add-In for Microsoft
Office, users of Excel can seamlessly leverage the power of SAS analytics
while providing secure access to data and IT resources previously
unavailable through Excel. The use of SAS Add-In for Microsoft Office
running under Microsoft Excel is demonstrated; including the use of cell
values and ranges as input and output to SAS® Stored Processes.
10:00 a.m.
SAS and Teradata Customer Roundtable
Bill Franks, Teradata Corporation
Join SAS and Teradata experts and joint customers for an informative
round-table discussion on how companies are using in-database
technology to improve marketing results, profitability, and customer
retention. Emphasis will be on why customers are choosing in-database
analytics to impact their initiatives, how to get started with an in-database
architecture, and key lessons learned. We’ll also discuss the types of results
to expect by running and optimizing key SAS processes within the Teradata
11:00 a.m.
Modernize with SAS® Dashboards: Go Beyond a
Collection of Gauges
Anand Chitale, SAS
Paper 038-2012
A modern dashboard’s ability to present data and information at both
summary and detailed levels makes it one of the most powerful tools in a
business user’s kit, going beyond a collection of dials and gauges and
meeting business needs in a practical and actionable way. The SAS® BI
Dashboard brings a powerful yet simple way to use an environment that
supports the design characteristics of a modern dashboard. This paper
showcases the characteristics of a modern dashboard and shows how you
can achieve the same with SAS BI Dashboard discussing industry-specific
dashboard examples.
Coders' Corner — Southern Hemisphere III
8:00 a.m.
Black Box PROCs: PROC LOGISTIC Discovered
Isabel Perry, Kaiser Permanente
Paper 087-2012
Black box procedures are incredibly useful for the modern statistician, but
they might not be aligned to what we think is happening behind the
scenes. Students might find themselves consulting many resources to
ensure that the code that they have just copied and pasted from an
Internet source is performing the theory that they have just learned from
their textbook. This paper combines statistical theory and the SAS® code
needed to implement a binary logistic regression analysis using health care
8:15 a.m.
Optimized 1:N Case-Control Match Using SAS
Zhiwei Wang, Center for International Blood and Marrow
Transplant Research, Medical College of Wisconsin
Paper 088-2012
In case-control match studies, when given a set of matching criteria, cases
can be matched with a large number of controls and vice versa. Randomly
selecting the matches might not lead to the maximum number of matched
pairs. An algorithm based on SAS® that optimizes a 1:N match is presented
in this paper. The algorithm uses an iteration-based approach. Two
calculated statistics are used to guide the selection process and to ensure
that an optimal pair is selected in every iteration. The resulting data set has
the maximum number of matched pairs, and the number of pairs are evenly
distributed among all cases. This algorithm can be applied to any number
of matching criteria. Examples of SAS code are given in each key step.
8:30 a.m.
Utilize Dummy Datasets in Clinical Statistical
Amos Shu, Endo Pharmaceuticsls
Paper 089-2012
Due to collectability or other issues, some clinical trial reporting tables like
physical examination, demographic characteristics, and some efficacy
tables usually need to be partially made up in some way in the real clinical
practice world. Creating dummy datasets is an effective way to improve
programming efficiency in these situations. This paper discusses five ways
to utilize dummy datasets in clinical statistical programming.
8:45 a.m.
Using SAS® to Get a Date: Integrating Google Calendar’s
API with SAS®
William Roehl, CrossUSA
Paper 090-2012
Google offers a powerful API that allows the more analytically and visually
powerful SAS to interact with and manipulate calendar data. By combining
the ease of Google calendaring with the power of SAS, businesses can
operate more efficiently, increase customer satisfaction, and analyze their
calendar data in nearly limitless ways. This paper illustrates how SAS can be
used to create, modify, and directly interact with Google Calendar data via
API calls. Using these calls, it is possible to retrieve available calendars;
import all calendar data such as date, time, location, etc.; as well as add,
delete, and modify preexisting calendars and their entries. This data can
then be analyzed in any number of ways available through the power of
9:00 a.m.
Batch Production of Driving Distances and Times Using
SAS® and Web Map APIs
Ash Roy, Canadian Institute for Health Information
Yingbo Na, Canadian Institute for Health Information
Paper 091-2012
This is a new methodology of using SAS URL access method and Web APIs
to run queries on an interactive Web site. This method will capture driving
distances and times from a Web map based on points marked by postal
9:15 a.m.
Multidimensional Scaling on ZIP Codes
Chao Huang, Oklahoma State University
Xiangxiang Meng, SAS
Paper 092-2012
Many marketing or customer relationship management activities require an
efficient solution to manage a number of ZIP codes. In SAS®, the
ZIPCITYDISTANCE function calculates the geographic distances between
any ZIP codes. And the MDS procedure translates the distance matrix of the
ZIP codes into relational numeric values. This paper describes a simple
solution that separates ZIP codes into limited levels based on the
multidimensional scaling and clustering methods. With SAS’s built-in ZIP
code and map data sets, two illustrations on Texas and Orlando, FL, are
introduced to show how to reduce a number of ZIP codes to manageable
9:30 a.m.
Three Simple Steps to Recovering and Inserting Data
Using Do Loops, Indexed Macro Variables, and PROC
SQL Update Statements
Stacey Collins, University of Michigan - Institute for Social
Paper 093-2012
When recovering data records from paradata or log files, it can be tedious
to parse and restore data to the correct variable within the data set,
particularly when the number or order of variables which contain data can
vary between records. This paper presents an efficient way to use do loops
and indexed macro variables to parse variable names and data from a
paradata file, and load them into the main data set using PROC SQL update
statements. This code is useful for restoring records one at a time, and does
not require the programmer to hard code any variable names or variable
orders for the purpose of inserting the data. The code is presented in SAS®
9.2 in a windows environment.
9:45 a.m.
Managing Analytic Processes with Paired SAS® Utility
Zhongwen Huang, Walgreens
John Hou, Walgreens
Paper 094-2012
A pair of macros was developed to enhance user analytic process
management in interactive SAS sessions. %_mStart(), the preprocessing
macro, creates a relative path system independent from hard-coded
absolute paths and is executable without program modifications when
copied to a different location. In addition, %_mStart() can back up SAS
source code automatically while the program is submitted for executing.
The backed-up SAS program will have date and time stamp added to the
original file name, serving the purpose of version control which is not
directly available in a typical analytical SAS environment. Following the end
of execution of the program, a post-processing macro %_mEnd() detects
error and warning messages in a SAS log window and displays them in a
pop-up window.
10:00 a.m.
SAS® Output Delivery System ExcelXP Tagset:
Customizing Cell Patterns, Borders, and Indention
Deepak Asrani, Medtronic, Inc
Paper 095-2012
The SAS® Output Delivery System ExcelXP tagset offers the most flexible
way to write SAS output to Microsoft Excel. Standard customizable options
in the ExcelXP tagset handle most of the Excel formatting very well.
However, given the ever-growing formatting features in Excel, there is
always a need to go beyond what is available. This paper describes how to
do some of the Excel formatting that requires modification of the standard
ExcelXP tagset. Specifically, this paper concentrates on customizing cell
patterns, borders, and indention.
10:15 a.m.
11:00 a.m.
Translating Foreign Language in SAS® with Google
Murphy Choy, School of Information System
Using SAS® to Manage SAS® Work Area Usage
Urvir Palan, Barclays Technology Centre
Paper 096-2012
SAS platform administrators always feel the pinch of not having enough
space in the SAS work area, even though they plan for the worst. There are
multiple approaches to tackle this problem, but one of the better ones is to
initiate the alert mechanism as soon as you see the first sign of fire.
Increased levels of global operation have resulted in companies having
business in many different geographical regions of the world. This move
necessitates the operation to be relatively localized and, thus, results in
databases with extensive amounts of information to be captured in a
foreign language. Often this creates difficulties in analytic projects that are
done by English-speaking analysts operating in non-English-speaking
environments. With the advent of Google Translate services, we will
demonstrate how a simple command issued to Google can be used within
SAS to generate the translated results.
Paper 099-2012
11:15 a.m.
Generation Why: How Generation Data Sets Can Help
Lisa Eckler, Lisa Eckler Consulting Inc.
Paper 051-2012
10:30 a.m.
How to Dynamically Conditionalize a SAS® Data
Integration Studio Job
Riku Jokinen, Aureolis
Paper 097-2012
Data-driven conditional processes in SAS have always been possible with
macros. With SAS Data Integration Studio, you might find macro-based
solutions either unwanted due to most of the code not being visualized in
the job, or impossible due to metadata not being able to follow the actual
data. The Loop transformation can be used to dynamically conditionalize
SAS code without using user-written macros. This enables data-driven SAS
Data Integration Studio jobs that will perform certain parts of the code only
if defined conditions apply. It also allows separate parts of the code to be
run either iteratively or conditionally while maintaining metadata intact
throughout the job.
10:45 a.m.
An Advanced, Multi-Featured Macro Program for
Reviewing Logs
Chris Swenson, UW Health
Paper 098-2012
An important, time-consuming task for any level of SAS® user is reviewing
the log for issues. Further, if there is no notification or plan in response to
the notification, essentially no review occurred. There are several macros
that check the SAS log for issues, and here we present a new macro
program that adds several new features to the existing paradigm that assist
with responding to issues. The macro includes capabilities to check internal
and external SAS and logs not from SAS; to include keywords and/or
exclude phrases from the search; to modify the notification behavior using
a pop-up message, email, and/or sound; to “recreate” the log in the current
interactive SAS session for review; and to abort the program should issues
Generation data sets are powerful tools available in SAS® to manage
versions of data. This paper will address what generation data sets are, how
they are defined and referred to, and why you should use them to improve
programming productivity and achieve simple and elegant management of
historical versions of data in SAS.
11:30 a.m.
Mining and Merging DATAMONITOR and WRDS
Databases with SAS®
Niam Yaraghi, State University of New York (SUNY at Buffalo)
Rajiv Kishore, State University of New York (SUNY at Buffalo)
Rui Chen, Ball State University
Paper 102-2012
In this paper, we show how a DATAMONITOR database can be grouped to
public and private companies based on ticker-symbol databases of
NASDAQ, AMEX, and NYSE. Moreover, we show EVENTUS software output is
cleaned and merged with the public companies databases.
Customer Intelligence — Northern Hemisphere
8:00 a.m.
CSI: Customer Segmentation Intelligence for Increasing
Darius Baer, SAS
Paper 103-2012
What will your customer do next? Customers behave differently; they are
not all average. Can you simultaneously meet your customers’ needs and
improve profitability? You can by communicating and providing better
offers to customers based on their behavior and demographics.
Segmentation gives you the ability to group customers in many ways: 1)
Business rules; 2) Supervised clustering – decision trees, and so on; 3)
Unsupervised clustering; 4) Creating segments based on quantile
membership. Which one works? That depends on two factors: the business
goal and customer attributes. Do you want to increase share of wallet,
market share, customer satisfaction, or all three? This presentation covers
roles played by business issues and available data and which SAS®
segmentation technique is appropriate for particular situations.
8:30 a.m.
10:30 a.m.
Classification of Customers’ Textual Responses via
Application of Topic Mining
Anil Pantangi, Oklahoma State University
Goutam Chakraborty, Oklahoma State University
Customer Experience Modeling
Estelle Marianne, Telstra
Nick Merry, Telstra
Wendy Au, Telstra
Paper 104-2012
Paper 107-2012
Customer satisfaction surveys play a vital role in monitoring business
performances in most industries. Typically, customer satisfaction surveys
are a blend of closed-end questions (numeric responses) and open-ended
questions (textual) leading to a collection of structured and unstructured
data. Textual comments are generally cumbersome and time consuming to
summarize and analyze. Sometimes, businesses use experts to rate
unstructured data to understand the nature and the valence of customers’
responses. In this paper, we illustrate the application of Topic Mining, using
SAS® Text Miner; to first categorize customers’ responses collected via a
survey of customers of a B2B (business-to-business) company. Then, we use
the topics to build a predictive model to automatically classify the
responses into negative versus non-negative categories.
Large customer bases will always have a number of customers who “fall
through the crack.” The impact to customers involved can be huge, and
brand image has the potential to be disproportional to the root cause of
the incident. For Telecommunications, the introduction of products and
services will deliver a continuous stream of “root causes” in terms of bad
customer service. The authors have employed predictive analytics to
provide the business with an opportunity of remediating these issues,
before the customer feels compelled to take action. Building robust sources
of customer interaction data and an automated scoring environment has
made possible to deliver highly effective ‘customer dissatisfaction’ scores to
front of house. This provides a valuable ‘last chance’ opportunity to solve
serious customer service issues.
9:00 a.m.
11:00 a.m.
Using SAS® and Vertica to Increase Online Effectiveness
and Revenues
Stephen Schultz, HP
Net Lift Model for Effective Direct Marketing Campaigns
Roman Kubiak,
(Invited) Paper 105-2012
Paper 108-2012
Many organizations have been able to minimize the effect of these
limitations by building their own customer behavior warehouses. These
warehouses are created with not only the clickstream data, but have
integrated web log data, social media information, sentiment analyses and
other informational sources. All the data adds up quickly and the overall
cost of maintaining these systems becomes increasingly difficult to
shoulder. The underlying databases soon become overwhelmed with the
sheer amount of data, analysis slows down due to performance reasons,
and soon the cost of continually upgrading the hardware to keep these
systems going becomes a major pain point. These customers have used
Vertica and SAS to provide an option that provides business results at
affordable prices.
This paper describes the basic concepts, benefits, and challenges of
implementing net lift models in direct marketing campaigns at Net lift models predict which customer segments are
likely to make purchases only if prompted by a marketing undertaking. The
modeling work was conducted using stepwise logistic regression in SAS®
Enterprise Miner™. The paper provides examples of how net lift probability
decomposition models leveraged differences between purchasers in the
test group and control group. This information was used to predict which
customer segments needed a marketing contact and which customer
segments were likely to make purchases without a nudge.
10:00 a.m.
Better, Consistent Customer Experience from
Analytically Based Real-Time Decisions
Toshi Tsuboi, SAS
Community Detection to Identify Fraud Events in
Telecommunications Networks
Carlos Andre R. Pinheiro, Oi Telecom
Paper 106-2012
Telecommunications’ industry evolves into a high competitive market
which demands companies to establish an effective revenue assurance
framework. Social network analysis can be used to increase the knowledge
about the customers’ behavior, not just in terms of individual usage but
mostly in relation to the customers’ connections and how they create
communities according to their call and text messages. By performing
community detection, telecommunications companies are able to
recognize groups of customers which unexpected behavior in terms of
usage and also in regard to types of social structures. Outliers groups might
be pointed out as suspicious communities in terms of fraud events,
delivering a relevant knowledge about possible leakages of money.
11:30 a.m.
Paper 109-2012
Consumer expectations from their interactions with business have
increased tremendously. Today, they expect that businesses, armed with
technology and customer databases, should be able to provide a relevant,
consistent customer experience across all channels. Unfortunately, this is
not often the case since data is underutilized, business processes are
disjointed, and analytics are not leveraged to make the optimal decisions.
As a result, customer loyalty and revenue opportunities are lost. This
presentation describes how organizations can use SAS® products, including
SAS® Real-Time Decision Manager and SAS® Model Manager, to apply SAS
analytics to improve customer experience by providing real-time analyticbased decisions to channels and business processes that drive consistent,
personalized customer experiences. This presentation provides a how-to
overview of the solutions and utilization examples.
Hands-on Workshops — Southern Hemisphere II
8:00 a.m.
Getting Up to Speed with PROC REPORT
Kimberly LeBouton, K.J.L. Computing
(Invited) Paper 158-2012
Learning the basics of PROC REPORT can help new SAS® user avoid hours of
headaches. PROC REPORT can often be used in lieu of PROC TABULATE or
DATA _NULL_ reporting--two areas that have driven the new SAS user
crazy! With the added capabilities of ODS, PROC REPORT can look as sharp
as a Microsoft Excel report. This paper will show how to use PROC REPORT
in both a windowing and non-windowing environment using SAS® 9.
Hands-on Workshops — Southern Hemisphere I
8:00 a.m.
Taking Full Advantage of Your SAS®
Don Henderson, Henderson Consulting Services
Art Carpenter, CA Occidental Consultants
(Invited) Paper 157-2012 is becoming the clearing-house for technical
information related to the use of SAS software. The site is managed and run
by SAS users for SAS users. It is free and open to all SAS users to browse.
Any SAS user can contribute to the site; just create an ID in order to
contribute new content or to expand upon existing content. Learn how
even small contributions can enhance the site for everyone. Join the
thousands of other SAS users that are a part of the creation of a resource
that is greater than the sum of its parts.
especially to large business problems. Optimization improvements include
faster problem generation and support for additional specialized solution
methods in the OPTMODEL procedure. Other new capabilities provide
derivative-free optimization, focusing on local search methods. SAS/OR 12.1
can also exploit multicore computing in local search optimization, in an
updated version of the nonlinear programming multistart method, and in
underlying methods for the LP, QP, and NLP solvers. Other updates include
an expanded set of constraint classes for the CLP procedure and enhanced
SAS® Simulation Studio support for large models and large experiments
(many factors and responses).
9:00 a.m.
The Traveling Salesman Traverses the Genome: Using
SAS® Optimization in JMP® Genomics to build Genetic
Kelci Miclaus, SAS
Rob Pratt, SAS
Matthew Galati, SAS
Paper 160-2012
Agronomic research employs genomics to develop breeding strategies that
improve the disease resistance, health, and yield of agricultural crops. Plant
genome complexity necessitates understanding how DNA markers across
the genome are related by building genetic maps that group and order
markers based on their inheritance. This biological challenge is an ideal
application of optimization routines common in operations research.
Optimal marker order can be formulated as the famous traveling salesman
problem, where we follow a path through the genome that returns the
shortest genetic distance map. Minimum spanning trees can group markers
using an undirected graph framework. Using algorithms from the
OPTMODEL Procedure in SAS/OR® implemented in a visual interface with
JMP Genomics, biologists can access powerful optimization algorithms for
building and viewing genetic maps.
10:00 a.m.
9:30 a.m.
Encore Presentation of Popular Topic (TBD) - HOW I
The Traveling Salesman Problem: Optimizing Delivery
Routes Using Genetic Algorithms
Sabah Sadiq, Institute for Advanced Analytics - Student
(Invited) Paper 161-2012
Hands-on Workshops — Southern Hemisphere II
10:00 a.m.
Encore Presentation of Popular Topic (TBD)- HOW II
Operations Research — Oceanic 1
The purpose of this paper is to discuss the methodology of optimizing
delivery route scheduling using genetic algorithms to solve the Multiple
Traveling Salesman Problem (mTSP). The traveling salesman problem (TSP)
is a combinatorial optimization problem where a salesman must find the
shortest route to n cities and return to a home base. While the TSP restricts
itself to one salesman, the mTSP generalizes the problem to account for
multiple salesmen. In order to optimize delivery routes, clustering will be
used to transform the mTSP problem into a set of traditional TSP problems.
The single TSP problems will then be solved using genetic algorithms.
Finally, the solutions will be visualized using PROC SGPLOT.
8:00 a.m.
New Features in SAS/OR® 12.1
Ed Hughes, SAS
Manoj Chari, SAS
Paper 159-2012
SAS/OR 12.1 debuts a broad range of new capabilities and enhanced
features in operations research. This paper surveys these additions,
emphasizing their benefits and their application to business problems—
10:00 a.m.
11:30 a.m.
Using SAS® to Measure Airport Connectivity: An
Application of Weighted Betweenness Centrality for the
FAA National Plan of Integrated Airport Systems (NPIAS)
Hector Rodriguez-Deniz, University of Las Palmas de Gran
Bringing Optimization to the Business: Interfacing
SAS/OR® with SAS® Stored Processes, Microsoft Excel,
SAS® Enterprise Guide®, SAS® Forecast Studio, and
Microsoft Project
Andrew Pease, SAS
Paper 162-2012
Paper 165-2012
The US Federal Aviation Administration (FAA) estimates that $52.2 billion
will be available over the next five years (2011-2015) to fund airport
infrastructure developments. Because one of the main objectives is to
reduce congestion and delays, there is a need to acknowledge the
importance of connectivity (measured with a centrality indicator) when
establishing funding priorities. Currently, the FAA does not do this. In this
paper, we expand an existing SAS/IML® implementation of betweenness
centrality to handle passenger-weighted airport networks, construct a
graphical representation of the US air transport network from airline
ticketing data, test the module to identify hub airports, and produce stylish
output using SAS® GMAP. Performance and complexity considerations of
the new algorithm are addressed.
SAS/OR® software provides a powerful array of optimization, simulation,
and project scheduling techniques to identify the actions that will produce
the best results, while operating within resource limitations and tight
restrictions. This paper focuses on ways to get this information to business
users in an intuitive, interactive way. Via SAS® Stored Processes, users can
change parameters and run different configurations of a base SAS/OR
program. These stored processes can be surfaced via the SAS® Add-In for
Microsoft Office, SAS® Enterprise Guide®, and SAS® Forecast Studio. Also, via
Microsoft Project macros, Microsoft Project users can export parameters to
SAS/OR, which produces optimized planning, and push back to the
Microsoft Project user. The technical setup of these various channels is
explored in demonstrations.
10:30 a.m.
Comparing Stock Returns Forecasting Methods Using
Wei Wang, University of Arizona
Arthur Li, City of Hope/University of Southern California
Paper 163-2012
The accuracy of forecasting stock returns is the key component to
generating profits on Wall Street. There are many methods to forecast stock
returns. Almost all data mining methods involve creating analytical models
based on historical data trends. Choosing the best forecasting method is
essential to obtaining fruitful stock returns. SAS® provides a flexible
platform that enables you to easily compare forecasting methods. In this
paper, we compare the three most commonly used technical trading
methods (moving average, Relative Strength Index, and Bollinger Bands). In
this comparison, we use SAS based on historical stocks from 1980 to 2010.
All of the calculations are performed using the DATA step or SAS macros.
The comparison generated from the program helps us decide the best
forecasting method.
11:00 a.m.
Formation of Optimum Accountable Care Organizations
(ACOs) Leveraging SAS/OR®
Khasha Dehnad, AIMS Consulting
Paper 164-2012
Under the new health care reform law, a network of healthcare providers
can form an “Accountable Care Organization (ACO)” and be awarded the
responsibilities of managing and delivering all of the healthcare needs of
Medicare beneficiaries. Discover how SAS/OR can be leveraged in the
formation of Accountable Care Organizations. The use of SAS PROC
OPTMODEL to solve this practical healthcare problem is explored in detail.
Planning and Support — Northern Hemisphere
8:00 a.m.
Services R Us
Kathy Council, SAS
Larry Stewart, SAS
Annette Harris, SAS
Paper 191-2012
SAS® is known for its world-class support and services. But how do you
make the most of the services from SAS? Where do you start? How do you
navigate the sea of information available? How do you find the resources
that you need to do your job? This presentation takes you through and gives you practical tips, tricks, and techniques to find
exactly what you need to use SAS. Whether you are a new or a seasoned
SAS user, you will learn something new that will help you become an even
more proficient SAS user.
9:00 a.m.
Consulting: Critical Success Factors
Kirk Lafler, Software Intelligence Corporation
Charles Shipp, Consider Consulting, Inc.
Paper 192-2012
The consultants of today require different skills than the consultants of
yesterday. Today's consultants are just as likely to have an MBA degree as a
technical degree. They tackle a wide variety of business and technical
problems and provide solutions for their clients. This presentation describes
the consulting industry from the perspective of these different types of
organizations (for example, Big Five accounting firms or organizations that
could be described as elite, boutique, independent, or IT). Specific attention
is given to the critical success factors needed by today's and tomorrow's
9:30 a.m.
SAS® User Groups: Why? How?
Rex Pruitt, PREMIER Bankcard, LLC
Paper 196-2012
This paper is about how to effectively establish and/or support a SAS User
Groups at any level (I.e., Regional, Special Interest, Local, or Internal). SAS
software is the mainstay of many successful organizations. However,
leveraging the success of any SAS software installation is completely
dependent upon its user base. Too often, organizations adopt, knowingly
or not, the idea that if they buy a SAS software solution, their employees
will use it effectively. Establishing and supporting SAS User Groups is
proven to generate positive returns. Resulting interactions amongst SAS
Users fosters healthy collaborative relationships that enhance their
performance. In this paper, I will cite experiences and specific examples of
SAS User Group 1) ROI, 2) support, and 3) establishment.
10:00 a.m.
The Systems Development Life Cycle (SDLC) as a
Standard: Beyond the Documentation
Dianne Rhodes, U.S. Census Bureau
Paper 194-2012
Has your company adopted the Systems Development Life Cycle (SDLC) as
a standard for benchmarking progress on a project? Have they developed
Microsoft Word and other templates for documents created during SDLC?
With the emphasis on the documentation and not on the analytical work
behind them, the project still falls behind schedule because of missed
requirements. If the requirements are not thoroughly complete when
coding begins, it is likely to fail in the testing phase, especially if the
independent test team gets a better, more complete version of the
requirements than the development team.
10:30 a.m.
SAS® and Microsoft SharePoint: Project and Resource
Management Tools and Techniques for Large, Globally
Distributed Programming Teams
Stetson Line, Amgen, Inc
Paper 195-2012
Most large companies employ a variety of in-house, off-shore, and service
provider resources. Virtual staff members often work in a variety of timezones and can have different vacation and holiday calendars based on local
ethnic and religious customs. How can managers effectively plan for
resource demand peaks and valleys in such an environment? A simple and
scalable approach using SAS and MS SharePoint will be presented that
provides a useful framework for both long-term forecasting and short-term
load-balancing decisions in the management of globally distributed teams.
11:00 a.m.
Lean and Mean: Using Lean Six Sigma to Improve Your
Analytic Processes
Robbie Reynolds, Aegon Direct Marketing Services
Rachel Alt-Simmons, SAS
Paper 193-2012
Many businesses have increased their analytic sophistication, with analytics
becoming more pervasive in business processes. With the increase of
analytic maturity, investments in the people, methodologies, and
technologies needed to effectively manage those processes have lagged.
Many analytic teams are tied up in managing production analytic
processes, and often lack a framework for ensuring process quality and
efficiency. In this session, we help analytic teams better manage these
processes, as well as reduce errors and cycle time through a lean Six Sigma
framework. The Life & Protection division of Transamerica puts the
framework to work in making significant improvements across its
marketing campaign optimization process.
Programming: Beyond the Basics — Asia 5
8:00 a.m.
Implementing Control Selection Using Hash Tables: A
Case Study
Craig Kasper, Manitoba Health
Paper 236-2012
This paper discusses a program written to perform matched control
selection from a research population, using hash tables to eliminate the
need for a large temporary data set, and allowing the process to run
significantly faster as a result. It describes the development of the program
from the point of initial need to the completion of the working program,
and discusses how insights into the control selection process enabled the
transformation of the program from using conventional methods to one
using dynamic programming.
8:30 a.m.
The SAS® Log: A Wealth of Data and Job Flow
Steven First, Systems Seminar Consultants, Inc.
Paper 237-2012
There have been many programs and papers written about reading the
SAS® log for error checking and warnings. Although that information is
valuable, we have found that the data messages that include filenames, row
counts, and other information are a wonderful source of run-time metrics.
This is where the real value of the SAS log is. These metrics, along with
metrics provided by PROC SCAPROC, can be used to automate and validate
run results, debug errors, provide job flow information and job
optimization, and enable grids. This paper discusses the jobs that we have
developed to use this neglected source of information.
9:00 a.m.
Copy and Paste Almost Anything
Arthur Tabachneck, myQNA
John King, Ouachita Clinical Data Services, Inc.
Nate Derby, Stakana Analytics
Randy Herbison, Westat
Richard DeVenezia, Independent Consultant
Ben Powell, Genworth Financial
(Invited) Paper 238-2012
Every day, data appears on computer screens in the form of spreadsheets,
wiki pages, HTML, PDF, Word documents, or any of the methods that are
used to display data forms and tables. And with any of those formats, you
can typically highlight and copy only the data you desire to your
computer's clipboard. However, because there currently isn't a PROC
IMPORT dbms=clipbrd option, how can you paste this data into a SAS® data
set? The present paper provides code that we believe can be used to
accomplish most such tasks and, at the same time, provides examples of
features that we think should be available in PROC IMPORT for all DBMS
10:00 a.m.
Optimizing That Which “…cannot be optimized….”
Superfast SAS 9.2 + Searches and Fuzzy Linkage of Large
Data Sets
Sigurd Hermansen, Westat
(Invited) Paper 239-2012
Some of the more successful innovations in the SAS® System have
percolated up through the listserv SAS-L and other sounding boards for
SAS users. This review of large-scale search and fuzzy linkage methods
focuses on questions and commentaries that have led to new techniques
and methods. In turn, SAS has incorporated these innovations into the later
releases of the SAS System.
9:00 a.m.
Leave Your Bad Code Behind: 50 Ways to Make Your
SAS® Code Execute More Efficiently
William Benjamin Jr, OWL Computer Consultancy,LLC
Paper 257-2012
This laundry list of tips shows 50 ways to help SAS programmers make their
code run faster and more efficiently. Topics include maximizing each DATA
step, making simple tasks take less code, using macro variables to simplify
maintenance, using built-in features, optimizing code to save disk space,
using sorts for more than just sorting, and ways to make the program code
just read better.
9:30 a.m.
Common Sense SAS® - Documenting and Structuring
Your Code
Gary Pool, BNSF Railway
11:00 a.m.
Paper 258-2012
“There’s an App for That”: It’s Called SAS® ODS! Mobile
Data Entry and Reporting via SAS ODS
Michael Drutar, SAS
Job security does not result from being the only one who can fix your
programs. It results from being the one who is most productive and able to
pass projects on to someone else. The most frightening thing that
confronts a SAS® programmer, whether amateur or professional, is to be
presented with the challenge of debugging or updating someone else’s
code. Two simple things can make your code more valuable: effective
documentation and good code structure. This paper shows the importance
of documentation and offers suggestions on how to make it effective. It
demonstrates simple techniques for creating clear, easy to read, easy to
debug, and easy to update code.
Paper 240-2012
Most mobile reporting allows users only to receive reports; however, it is
often necessary to INPUT data on a mobile device. This can be
accomplished by leveraging Google spreadsheets and SAS ODS. This
paper’s example explains how a Cross Country Coach records a runner’s
race times (in real time) on a Google spreadsheet using his mobile device.
His office computer has a SAS® job which, via the filename statement, reads
the updated Google spreadsheet into SAS. SAS processes this data and
sends an email containing an embedded HTML dashboard of Runner KPI
dials, charts and/or tables. The Coach receives this report almost
instantaneously. Because it is an embedded email, this solution works on
nearly any mobile device (for example, iPhone or Android).
10:00 a.m.
Graphing Made Easy with SG Procedures
Lora Delwiche, University of California, Davis
Susan Slaughter, Avocet Solutions
(Invited) Paper 259-2012
Programming: Foundations and Fundamentals —
Asia 4
8:00 a.m.
The Use and Abuse of the Program Data Vector
Jim Johnson, Ephicacy Consulting Group, Inc.
(Invited) Paper 255-2012
Have you ever wondered why SAS® does the things that it does, or why
your programs get away with the things that they do, or why SAS does not
do what you want it to? A key operational component of SAS is the
program data vector. Knowing how the program data vector functions
helps programmers better understand how SAS works. This paper helps
you understand how the program data vector works, how DATA steps use
it, and how you can exploit, manipulate, and trick it. Many examples are
included. The magic behind the DOW loop and other mysteries are
discussed. There is something in this paper for all levels of programmers,
from the beginner to the most advanced.
Using the Statistical Graphics (SG) procedures, introduced with SAS® 9.2,
you can create a wide variety of high-quality graphs with just a few lines of
code. This paper covers the three basic SG procedures—SGPLOT, SGPANEL,
and SGSCATTER. SGPLOT produces single-celled graphs. SGPANEL
produces multi-celled graphs that share common axes. SGSCATTER
produces multi-celled graphs that may use different axes. This paper shows
how to use each procedure to produce different types of graphs, how to
send your graphs to different ODS destinations, how to access individual
graphs, and how to specify properties of graphs, such as format, name,
height, and width.
11:00 a.m.
A Different Point of View with ODS PDF in SAS® 9.3
Scott Huntley, SAS
Woody Middleton, SAS
Paper 260-2012
The ODS PDF statement in SAS 9.3 is providing new ways to change how
you view and display your output. Several enhancements in the ODS PDF
statement are sure to be crowd pleasers. Topics in this paper include: how
to change orientation mid-file, how to drill down from your PDF file, how a
stronger use of vector-based graphics saves memory and time, and much
more. Be the first to find out how to change your output and get the
different point of view you’ve been wanting.
Reporting and Information Visualization —
Southern Hemisphere IV
8:00 a.m.
Using SAS/GRAPH® to Create Visualizations That Also
Support Tactile and Auditory Interaction
Ed Summers, SAS
Robert Allison, SAS
Julianna Langston, SAS
Jennifer Cowley, SAS
Paper 279-2012
Concepts, ideas, and analyses are commonly presented as graphics that are
optimized for visual consumption. Does that mean that blind students and
professionals are out of luck? Not anymore. This presentation demonstrates
best practices for multimodal visualizations for blind users of the iPad and
other touchscreen mobile devices. Multimodal visualizations allow blind
users to interactively explore visualizations through touch, discover details
through sound, and comprehend the essence of the visualizations without
vision. You learn best practices for a variety of common charts, plots, and
maps. We demonstrate how to create multimodal visualizations using SAS
macros that encapsulate the best practices. Lastly, we explore how an
auditory channel can improve the usability of visualizations for sighted
9:00 a.m.
Innovative Uses of ODS and GTL
Kathy Chen, Genetech Inc. Part of Roche Group.
Paper 280-2012
Graphically representing treatment effect is often easier to understand and
is more frequently used with summary reports. The rollout of the SAS®
Output Delivery System (ODS) has facilitated the automatic creation of
statistical graphics. The ODS Graph Template Language (GTL), when used
with a DATA step or PROC SGRENDER, enables you to design your own
layout so that you can easily incorporate the statistical graphics into
summary reports. The paper describes how to use ODS graphics and GTL to
incorporate the dynamic visualization of data within the body of a summary
report table. Topics include creating statistical graphics from SAS
procedures with ODS and customizing summary reports by incorporating
graphics using GTL.
9:30 a.m.
Make an Appropriate Page Break in a PDF When Using
Xia Shan, Chinese Financial Electrical Company
Paper 389-2012
When using PROC REPORT to generate a PDF file, SAS® will not split two
group values if the current page can’t hold the next group value any more.
What we need is that when the current page can’t hold the next group
value we want to push the next group value into the next page (i.e., make a
page break at appropriate position). This paper tries to solve this problem.
10:00 a.m.
Traffic Lighting: The Next Generation
Julie VanBuskirk, Baylor Health Care System
Jennifer Harper, Baylor Health Care System
Paper 282-2012
Traditional traffic lighting is a tool intended to separate data into three
categories highlighted with bright colors based on performance. However,
if all the cells in a table are boldly colored, the reader is unable to achieve
their goal of easily sorting between good and bad results. We sought to
apply visual design changes to our tables to reduce the amount of
decoration and focus on what was important, the data! Typically, traffic
lighting is done using PROC FORMAT; however, our data cells contained
text strings which required a more complex use of style options, COMPUTE
blocks, flag variables, and macros to implement. However, all this is quite
doable in SAS®, and the results were a much more effective table delivered
to our partners.
10:30 a.m.
An Automatic Approach to Creating a Data Dictionary in
SharePoint Using SAS®
Kevin Chung, Fannie Mae
Paper 283-2012
You might have several data sets created by SAS® applications, and you
want to share this data with users. This paper illustrates how to use SAS to
create a data dictionary for any existing SAS data set, and how to store the
result in an HTML file in Microsoft SharePoint. A data dictionary is a
collection of information about data such as name, attribute, definition,
source, data type, and length. SharePoint is a Web application platform
developed by Microsoft. It is widely used by divisions and departments in
an enterprise as a portal to communicate with internal and external users.
11:00 a.m.
Together at Last: Spatial Analysis and SAS® Mapping
Darrell Massengill, SAS
Jeff Phillips, SAS
Randy Tobias, SAS
Paper 284-2012
Spatial analysis and maps are a perfect match. Spatial analysis adds
intelligence to your maps; maps provide context for your spatial analysis.
The geostatistical tools in SAS/STAT® software can model and predict a
variety of spatial data. SAS mapping tools enable you to create rich
visualizations from that material. This presentation introduces a new
framework that combines SAS spatial analytics with SAS mapping.
Examples demonstrate how you can use the SAS/GRAPH® ANNOTATE
facility with the transparency specification (new in SAS® 9.3) to combine a
predicted spatial surface with traditional SAS/GRAPH® maps, and show how
to tap into the additional mapping resources of ESRI software through the
SAS® Bridge for ESRI. These tools empower you to make more intelligent
maps and more informative spatial analyses.
Retail — Asia 1
9:00 a.m.
8:00 a.m.
Regular Expressions in SAS® Enterprise Guide®
Mark Tabladillo, MarkTab Consulting
SAS® Regular Price Optimization Solution: Customer
Case Study
Manoj Chopra, Michaels Stores
(Invited) Paper 421-2012
9:00 a.m.
Price Optimization - Regular Price Optimization
Dave Eddy, Sobey's
(Invited) Paper 423-2012
As competition increases for the consumer's dollar, the promotional
product and price play an important role in the customer's decision. With
thousands of SKUs in a typical grocery store, Sobeys is incorporating SAS®
Promotion Optimization to help manage this important process. Sobeys is
one of two national grocery retailers in Canada. In this session, you will hear
how Sobeys is implementing a planning and pricing solution that will
identify opportunities to increase sales and margin, while reducing the
manual effort required to execute strategies. You will hear how SAS
Promotion Optimization is being implemented and how Sobeys is
integrating multiple sources of data to generate pricing recommendations.
10:00 a.m.
SAS® Retail Planning 7.2 Demonstration
Kerri Devine, SAS
Elaine Markey, SAS
Paper 287-2012
We demonstrate SAS Retail Planning 7.2. This demonstration will show how
this release helps retailers plan their financials and organize customercentric localized assortments in an effective and efficient manner.
SAS® Enterprise Guide® Implementation and
Usage — Northern Hemisphere E-4
8:00 a.m.
Not Just for Scheduling: Doing More with SAS®
Enterprise Guide® Automation
Chris Hemedinger, SAS
Paper 298-2012
SAS Enterprise Guide supports a rich automation model that allows you to
"script" almost every aspect of opening and running SAS Enterprise Guide
projects. While this is most often used with the built-in "scheduler" function
to simply run a project or process flow unattended, you can also write your
own scripts that automate much more. You can create new projects on the
fly, supply values for project prompts, run individual tasks, export results,
and more. You're not limited to the traditional VB Script method of
automation; you can also use more sophisticated frameworks such as
Windows PowerShell or Microsoft .NET. This paper describes the concepts
behind automation for SAS Enterprise Guide, and provides examples to
accomplish a variety of tasks using the different scripting technologies.
Paper 299-2012
In version 9, SAS® introduced Perl regular expressions (also known by the
acronym "PRX," the first three letters of these functions or call routines).
However, previous versions of SAS had regular expressions (known by the
acronym "RX," the first two letters of these functions or call routines). This
presentation describes specific functional and performance differences in
these two exclusive regular expression strategies and recommends when to
use each strategy. The technologies are compared using SAS Enterprise
Guide 4.2.
9:30 a.m.
Using SAS® Enterprise Guide® the Same Way as Base
SAS® and More
Rahman Sarker, RBC Royal Bank of Canada
Paper 300-2012
The server version of SAS Enterprise Guide has some limitations that can be
resolved by customizing the way that SAS Enterprise Guide gets connected
to the remote server. This paper talks about a customized usage of SAS
Enterprise Guide that will enable us to use SAS Enterprise Guide the same
way as Base SAS®; and some more unique usage of SAS Enterprise Guide
that can benefit SAS programmers with all skill levels.
10:00 a.m.
Productivity Tips for SAS® Enterprise Guide® Users
Steven First, Systems Seminar Consultants, Inc.
Jennifer First, Systems Seminar Consultants, Inc.
(Invited) Paper 301-2012
SAS Enterprise Guide is a versatile, revolutionary tool for everyone from
novice analysts to experienced programmers. This paper focuses on tips for
a wide variety of users. Topics include leveraging point-and-click
functionality, producing quick ad hoc analyses, organizing SAS processes,
increasing speed and accuracy in SAS, automating and streamlining
processes, creating attractive reports and graphs, learning how to code
what you want and avoiding what you do not, and leveraging new features
available in SAS Enterprise Guide. We discuss many quick time-saving tips
for analysts and programmers. This paper has something for any SAS
Enterprise Guide user and also has great information for someone who has
never used SAS Enterprise Guide but is interested in its capabilities.
SAS® Workshop Series — Asia 2
8:00 a.m.
SAS® Workshop: SAS® Add-In for Microsoft Office 5.1
Eric Rossland, SAS
Paper 412-2012
This workshop provides hands-on experience using the SAS Add-In for
Microsoft Office. Workshop participants will:
• access and analyze data
• create reports
• use the SAS add-in Quick Start Tools
9:00 a.m.
SAS® Workshop: SAS® Platform Administration
Christine Vitron, SAS
Paper 413-2012
This workshop provides hands-on experience using SAS® Management
Console to administer the platform for SAS® Business Analytics. Workshop
participants will:
• back up the metadata
• register a user in the metadata
• manage access to application features with roles
10:00 a.m.
SAS® Workshop: DataFlux® Data Management Studio
Kari Richardson, SAS
Paper 414-2012
This workshop provides hands-on experience using DataFlux Data
Management Studio to profile and then cleanse data. Workshop
participants will:
• learn to navigate DataFlux Data Management Studio
• define and run a data profile
• define and run a data job
11:00 a.m.
SAS® Workshop: SAS® Enterprise Guide® 5.1
Eric Rossland, SAS
Paper 415-2012
This workshop provides hands-on experience using SAS Enterprise Guide.
Workshop participants will:
• access different types of data
• analyze data using the Data Explorer
• create reports and analyses
Statistics and Data Analysis — Northern
Hemisphere E-1
8:00 a.m.
Analyzing Survival Data with Competing Risks Using
SAS® Software
Guixian Lin, SAS
Ying So, SAS
Gordon Johnston, SAS
Paper 344-2012
Competing risks arise in studies when subjects are exposed to more than
one cause of failure and when failure by one cause excludes failure by other
causes. For example, the cause of death (failure) in bone marrow
transplantation can be only one of several causes: relapse, graft-versus-host
disease, or other causes. The standard Kaplan–Meier method for survival
analysis does not yield valid results for particular risks when there are
competing risks. The SAS %CIF macro implements appropriate
nonparametric methods for estimating cumulative incidence functions. It
also implements the method of Gray (1988) for testing differences between
these functions in multiple groups. This paper presents the %CIF macro and
illustrates its application to analyzing survival in complex clinical trials.
Statistics and Data Analysis — Northern
Hemisphere E-2
8:00 a.m.
Enhanced Data Analysis Using SAS® ODS Graphics and
Statistical Graphics
Patricia Berglund, University of Michigan-Institute for Social
(Invited) Paper 349-2012
This paper presents practical examples of enhanced data analysis through
use of ODS Graphics and the Statistical Graphics (SG) procedures. SAS 9.3
ODS Graphics options and selected SG procedures are demonstrated with a
variety of analytic techniques including examination of variable
distributions and common regression methods. Procedures such as PROC
LOGISTIC, and PROC SURVEYLOGISTIC are used with accompanying ODS
Graphics and SG tools for enhanced analysis. The analysis applications
include unweighted and weighted analyses and, where appropriate, SAS
SURVEY procedures for analysis of data derived from a complex sample
design. The techniques presented here can be used in any operating
system, and are intended for an intermediate level audience.
Statistics and Data Analysis — Northern
Hemisphere E-1
9:00 a.m.
SAS® Tools for Cost-Effective and High-Quality Clinical
Trial Reporting
Paul Novotny, Mayo Clinic
Angelina Tan, Mayo Clinic
Nathan Foster, Mayo Clinic
Jeff Sloan, Mayo Clinic
Paper 345-2012
Two SAS reporting macros were developed and became very popular
analytic tools at the Mayo Clinic. These macros summarize continuous,
discrete, ordinal, and time-to-event data in RTF format, which can be
inserted directly into manuscripts or presentations. Macros are easy to
implement and flexible enough to be useful in a wide range of studies.
They reduce the costs of clinical trials (by reducing statistician turnaround
times), enable statisticians to be more productive, and enable the study
team to spend more time interpreting the data and less time searching
through pages of SAS output and creating reports. Macros also increase the
quality of reports and eliminate transcription errors. Their ease of use,
flexibility, accuracy, and high-quality output provide statisticians with
strong analysis tools.
Statistics and Data Analysis — Northern
Hemisphere E-2
decision tree results with and without Kass adjustments for binary target
variable and an interval target variable, also provides insights to Kass
adjustments/Bonferroni correction in decision trees.
9:00 a.m.
Including the Salesperson Effect in Purchasing Behavior
Philippe Baecke, Ghent University
Dirk Van den Poel, Ghent University
Paper 350-2012
Nowadays, an increasing number of information technology tools are
implemented in order to support decision making about marketing
strategies and improve customer relationship management (CRM).
Consequently, an improvement in CRM can be obtained by enhancing the
databases on which these information technology tools are based. This
study shows that CRM models shouldn’t limit their predictive variables to
information of the individual customer. The salesperson’s personal
attitudinal and behavioral characteristics can also have an important
impact on his sales performance. This salesperson effect can be easily
included by means of a generalized linear mixed model using PROC
GLIMMIX. This can significantly improve the predictive performance of a
purchasing behavior model of a home vending company.
Statistics and Data Analysis — Northern
Hemisphere E-1
9:30 a.m.
Deep Dive into the PIM and DDI Data
Michelle Hopkins, Stratis Health
Paper 346-2012
Through a contract funded by CMS, work was done to decrease the number
of Medicare beneficiaries who have been prescribed a potentially
inappropriate medication (PIM) and/or medications that could result in a
drug on drug interaction (DDI). SAS® 9 was used to analyze Part D claims
data to track progress on improving rates as well as taking a deeper dive
into the data to identify trends. From baseline to re-measurement,
Minnesota saw a relative improvement rate (RIR) of 29.3% for PIMs and
12.6% for DDIs. The nation saw RIRs of 15.4%, and 10.6%, respectively.
Minnesota’s biggest decrease was in the drug categories of narcotics. This
paper will show the analysis done, the SAS code used, and important
Statistics and Data Analysis — Northern
Hemisphere E-2
9:30 a.m.
Kass Adjustments in Decision Trees on Binary/Interval
Manoj Immadi, Oklahoma State University
Paper 351-2012
Kass adjustment maximizes the independence between the two branches
after the split. But how will these adjustments work on interval and binary
target variable is a big question? This paper describes split search algorithm
in decision trees for selecting useful inputs, followed by comparing the
Statistics and Data Analysis — Northern
Hemisphere E-1
10:00 a.m.
Selecting Unrestricted and Simple Random With
Replacement Samples Using Base SAS and PROC
David Chapman, Consultant
Paper 347-2012
This paper reviews techniques for selecting unrestricted and simple
random without replacement samples using data step code and
procedures such as PROC SORT and RANK. Random sampling basics are
given that discusses the UNIFORM random number function and special
SAS functions INT, CEIL,and FLOOR. Data step code for selecting Bernoulli
samples and two different approaches to selecting a simple random sample
without replacement are presented and discussed. Simpler ways to select
simple random samples using PROC SORT and PROC RANK are illustrated.
An alternative to selecting a random sample in the data step is to use PROC
SURVEYSELECT in SAS/STAT. The syntax for the SURVEYSELECT procedure is
given and discussed.References to published papers on how to use SAS to
select random samples are given.
Statistics and Data Analysis — Northern
Hemisphere E-2
10:00 a.m.
Wallet and Share of Wallet Estimation: A Flexible
Shira Witelson, Digitas
Paper 352-2012
In this paper, we demonstrate how Wallet and Share of Wallet estimation,
widely used in the credit card industry for marketing, can be applied in a
range of industries. The methodology consists of a series of steps,
beginning with primary research, and progressing to the use of
unsupervised learning method enabled by SAS®, predictive modeling and
statistical test techniques. The result is a flexible means for estimating the
most realistically attainable Wallet of a customer and thereby calculating
the customer’s Share of Wallet. Definitions: Internal Spend: Amount a
customer spends on the company’s products and services. External Spend:
Amount a customer spends on other providers’ products and services.
Formulas: Wallet = Internal Spend + External Spend Share of Wallet =
Internal Spend / Wallet
Statistics and Data Analysis — Northern
Hemisphere E-1
Statistics and Data Analysis — Americas Seminar
10:30 a.m.
11:00 a.m.
Simplifying the Analysis of Complex Survey Data Using
the SAS® Survey Analysis Procedures
Varma Nadimpalli, Westat
Katie Hubbell, Westat
Using SAS® for the Design, Analysis, and Visualization of
Complex Surveys
Sharon Lohr, Arizona State University
Paper 348-2012
Large surveys have design features like stratification, clustering, and
unequal probability of selection. The calculation of weights involves
nonresponse adjustments and raking. The analysis includes descriptive
statistics such as frequencies, means, and their standard errors. Standard
statistical software modules such as PROC FREQ and PROC MEANS
underestimate variance as they assume that the data is from a simple
random sample. The survey procedures such as SURVEYMEANS and
SURVEYFREQ that have been added to SAS/STAT® software can compute
variances that accurately reflect complex sample design and estimation
procedures. This paper compares the complexity of the variance estimation
code used in earlier projects with the simplicity of the code that is possible
using the survey analysis procedures.
Statistics and Data Analysis — Northern
Hemisphere E-2
10:30 a.m.
Measuring Consumer Involvement Profiles as a SecondOrder Construct Using SAS® PROC CALIS
Anurag Srivastava, Shanti Business School
Vikram Suklani, Shanti Business School
Pranav Karnavat, Shanti Business School
Paper 353-2012
Marketing scales have been used for measuring marketing-related
phenomena for the past 60 years. As the complexity of phenomena
increases, there is an increasing demand to use sophisticated techniques
for developing, testing, and modifying scales. One of the latest techniques
is the structural equation modeling (SEM) technique. The popular
marketing scales need to be validated with time. In this paper, a very
popular construct is discussed. A Consumer Involvement Profile is actually a
second-order construct, not a first-order construct as documented in
existing literature. Bibliographic research shows that when testing SEM,
LISREL and recently AMOS have been the software of choice. The use of
PROC CALIS is not as popular. The paper compares and contrasts the
process of scale modification using PROC CALIS and AMOS.
(Invited) Paper 343-2012
Visualizing data, finding estimates for population and model quantities,
and checking model validity are challenging in complex surveys because of
clustering, unequal weights, and other survey design features. SAS PROC
family are powerful tools for designing surveys and analyzing data from
complex surveys. Recent developments to these procedures make them
more powerful and more flexible than ever before. We present examples
from complex surveys to illustrate how the procedures may be used for
standard analyses as well as advanced applications such as graphing
complex survey data, performing model diagnostics, making inferences
employing the bootstrap, and combining data from multiple surveys.
Systems Architecture and Administration —
Northern Hemisphere E-3
8:00 a.m.
Oracle and SAS®: Clouds, Community, Collaboration, and
Computing Creativity; Goodbye Cloudy with a Chance of
Showers; Hello Cloud-eze and Clear Skies
Maureen Chew, Oracle Corporation
Thomas Mendicino, GE Capital
(Invited) Paper 385-2012
SAS and Oracle bring forth another year of innovation and collaboration.
This session highlights the convergence and intersection of this collective
effort including performance studies with SAS grid applications, Sun ZFS
Storage Appliance, Solaris 11, SPARC T4, Exadata, and Exalogic. Also
covered: Oracle and SAS R&D collaboration updates and steps toward SAS
program cloud readiness. Our community focus will highlight an
architecture and lessons learned from a corporate-wide, enterprise
environment supporting some 600+ SAS users. Running on a Sun Fire E25K
with 200+terabytes of operational data in an Oracle Exadata Database
machine, this user community represents specialties such as risk,
marketing, operations, finance, fraud, and collections using a wide range of
SAS applications from simple reporting, portfolio analytics, advanced
modeling, and forecasting.
9:00 a.m.
Utilize Red Hat Kernel Virtual Machine to Enable Your
Development and Test Environment to Peacefully CoExist with Your Production Environment
Bob Augustine, Hewlett-Packard
Barry Marson, Red Hat
Paper 375-2012
As x86–64-based servers, such as the HP ProLiant, have become less
expensive, increases in performance have enabled businesses to seek ways
to more effectively utilize them within their enterprises. Another industry
trend has created the need for businesses to be able to further subdivide
larger proprietary servers that have utilized using hard and virtual partition
technology. In order for a migration from these proprietary architectures to
be viable, there is a need to offer a migration methodology for
virtualization technologies to be made available on commodity hardware.
Because of SAS® software’s unique I/O footprint methods of virtualization
utilizing shared resources, typically enabled via a hypervisor have been
9:30 a.m.
Evolution of Best Practices for Metadata Change Control
in SAS® 9
Diane Hatcher, SAS
Paper 376-2012
The concepts for change control around the SAS® Metadata Server have
remained fairly constant throughout the releases across SAS® 9. The best
practices for how to manage the change process, though, has evolved as
the tools have evolved. This paper identifies some best practices for
implementing processes using the metadata promotion tools, comparing
SAS® 9.1.3, SAS® 9.2, and SAS® 9.3. This is intended for SAS system
administrators who are familiar with the SAS architecture and the role that
the metadata server plays. We focus on how to structure the metadata
environment, the tools available for handling changes in metadata, and
best practice processes that control how change occurs.
10:30 a.m.
Automagically Herding 101 SAS® Users from Microsoft
Active Directory to SAS Metadata
Stephen Overton, Zencos Consulting
Paper 377-2012
Creating users within SAS metadata can become a tedious task for the
system administrator, especially in large environments with strict
compliance policies around user access to data through SAS. This paper will
discuss a process and provide code to import users from Microsoft Active
Directory into SAS metadata. A stored process will be the graphical
interface for the security administrator to pick-and-choose what users will
be imported. This process can be extended further to import group
memberships. This paper will only focus on importing users. Using a stored
process to selectively import users from Active Directory streamlines user
creation in SAS metadata and provides a point and click method to
minimize human error.
11:00 a.m.
From Solo to Symphony: Scale Service Up Using Multiple
Stored-Process Server Clusters
Paper 378-2012
System architects today often face a difficult challenge: how to scale up
existing services to serve more clients, who not only have more requests
but also demand faster responses. The answer is to create a server cluster
with the support of load balancing. Clusters created using SAS Stored
Process Server provide a way to define a service in a metadata server,
balance its load for various clients by using Object Spawners, and execute
the implementation across different hosts to achieve the desired
performance. This paper shows how to set up a server cluster by
connecting multiple stored process servers and how to configure the load
Walt Disney World Swan and Dolphin Resort
Andrew T. Kuligowski, Conference Chair
SAS Global Forum is a smokefree conference. Thank you for
your cooperation.
Presentations can be recorded,
but only with permission from
the speaker.
Please turn off cell phones and
pagers during presentations.
Please refer to the SAS Global
Forum Guidelines for Participation
in your program guide for
more information.
Aanderud, Patricia 29
Adkins, Tony 13
Agravat, Manoj 24
Agrawal, Gaurav 26
Allison, Paul 23
Allison, Robert 67
Alt-Simmons, Rachel 65
Ames, Michael 11 , 36 , 48 , 49
Amezquita, Darwin 12 , 19
Andre R. Pinheiro, Carlos 62
Andruskevitch, Victor 26
Anstead, James 18
Antwerpen, Andres 36
Arnold, Tim 26
Asrani, Deepak 60
Atienza, Philamer 32
Augustine, Aaron 43
Augustine, Bob 27 , 71
Au, Wendy 62
Azimaee, Mahmoud 38
Baars, Frank 58
Bachtell, Kate 37
Baecke, Philippe 70
Baek, Eun 25
Baer, Darius 61
Bagnell, Melissa 14
Bahnsen, Alejandro 12 , 19
Barbalau, Iuliana 10
Barnhart, Mike 8
Battiston, Christopher 17 , 51
Bawa, Gurpreet 52
Beaver, James 29
Beese, Tim 59
Bellara, Aarti 24
Benjamin Jr, William 29 , 66
Bennett, Donna 26
Bentley, John 36
Berglund, Patricia 69
Bessler, LeRoy 26 , 45
Bianchi, David 57
Blair, Ed 55
Blomberg, Jodi 52
Boase, Jonathan 16
Bogacz, Stephen 57
Bogard, Matt 31
Borjesson, Ulf 50
Bost, Christopher 9 , 45
Bouedo, Mickael 46
Bresson, Christopher 58
Brown, Iain 12
Brown, Tony 56
Buck, Debbie 20
Bukkapatnam, Satish 55
Burke, Michael 50
Bursac, Zoran 53
Busby, Philip 35
Cai, Bo 16
Cai, Liping 13
Cai, Weijie 24
Campbell, Scot 22
Cano, Gabe 10
Canonizado, Katrina 18
Carpenter, Art 5 , 7 , 20 , 40 , 63
Case, Todd 52
Chakraborty, Goutam 10 , 12 , 17 ,
18 , 39 , 52 , 62
Chakravarthy, Raghunathan 44
Chapman, David 70
Chari, Manoj 63
Chen, Fang 24
Chen, Kathy 67
Chen, Min 41
Chen, Rui 61
Chen, Wei 13
Chew, Maureen 71
Chitale, Anand 8 , 50 , 59
Chopra, Manoj 68
Choy, Justin 32
Choy, Murphy 43 , 46 , 52 , 61
Christian, James 26
Chu, Hai 28
Chung, Kevin 67
Clouse, Amy 22
Clover, Lina 50
Cochran, Ben 46
Cody, Ronald 20
Cohen, John 45
Cohen, Robert 49
Cokins, Gary 13
Coles, Dragos 31
Collado, Evangeline 50
Collins, Keith
Collins, Stacey 60
Conway, Ted 36
Corliss, David 55
Coughlin, Margaret 33
Council, Kathy 64
Cowley, Jennifer 67
Cox, Gordon 5
Cox, James 49
Cox, Thomas 19
Coyle, David 8
Crawford, Peter 44 , 47
Crevar, Margaret 56 , 57
Cui, Xiangchen 16 , 41
Curat, Guillaume 29
Daniels, Aaron 17
Darwish, Ahmed 28
Davis, Scott 18
Day, Gavin 22
Dean, Jared 39
Decker, Chris 40
Dehnad, Khasha 64
DelGobbo, Vince 39
Delwiche, Lora 66
Derby, Nate 21 , 65
DeVenezia, Richard 65
deVille, Barry 42 , 52
Devine, Kerri 68
Dhillon, Rupinder 14
Dickey, David 54
Dietz, Alex 28
Dorfman, Paul 19 , 40
Dorfner, Greg 57
Droogendyk, Harry 45
Drutar, Michael 66
Duan, Rui 15
du, Anna 42
Duling, David 39
Dunlap, Davetta 6
Dunn, Jessica 22
Dunn, Toby 19
Désilets, Karine 30
Eberhardt, Peter 5 , 14
Eckler, Lisa 61
Eddy, Dave 68
Elkin, Eric 25 , 53
Elsheimer, Bruce 55
Ensor, Michele 6
Erinjeri, Jinson 35
Faria, Plinio 36
Faron, Michael 17
Fecht, Marje 14
Ferguson, Ann 21
Ferrari, Jim 27
Figallo-Monge, Manuel 7
First, Jennifer 68
First, Steven 65 , 68
Fisher, Thomas 55
Flis, Marty 58
Fogleman, Stanley 43
Foley, Richard 49
Foster, Nathan 69
Foty, Fuad 11
Franks, Bill 59
Fu, I-kong 50
Fu, Jizhou 21
Fuller, Jack 44
Gaeth, Gary 12
Galati, Matthew 63
Gallego, Lorrie 31
Gao, Yubo 25
Gardiner, Joseph 55
Garla, Satish 10 , 12 , 17 , 39 , 52
Garrett, Guy 8
Gayle, Brian 5
Gerlach, John 41
Ghosh, Sunita 37
Gibbs, Phil 53
Gilsen, Bruce 16 , 43
Gloudemans, Julie 16
Goklani, Sunil 28
Gonzalez, Andres 12 , 19
Gopal, Ram 42
Grandits, Greg 33
Granger, Erwan 57
Granger, Greg 59
Guerette, Mike 27
Gunawan, Steve 30
Guo, Xing 50
Gupta, Saurabh 22
Hadden, Louise 15
Hall, Angela 29 , 57
Haller, Susan 38
Hall, Johnston 29 , 47
Hallquist, Richard 31
Hamilton, Jack 44
Hampton, Jessica 38
Handelsman, David 15
Hantsch, Joseph 18
Han, Yanwei 41
Hara Sudhan Duraidhayalu, Hari
Harper, Jennifer 67
Harper, Renee 43
Harrington, Kristen 10
Harris, Annette 64
Harris, Bryan 22
Hatcher, Diane 8 , 72
Havens-McColgan, John 37
Hazejager, Wilbram 11 , 38
Healy, Ian 41
Hebbar, Prashant 46
Helbig, Tuesdi 31
Hemedinger, Chris 68
Henderson, Don 7 , 63
Hennessey, John 33
Herbison, Randy 65
Hermansen, Sigurd 66
Hill, Melissa 32 , 47
Hinson, Joseph 33
Holdaway, Keith 56
Hopkins, Michelle 70
Hou, John 60
Huang, Chao 34 , 60
Huang, Ling 13
Huang, Zhongwen 60
Hubbell, Katie 71
Huff, Gina 31
Huggins, Steve 56
Hughes, Ed 63
Hume, James 35
Hummel, Andrew 35
Huntley, Scott 66
Huynh, Nathan 16
Immadi, Manoj 70
Jagtap, Arvind 30
Jain, Adish 37
James, Chris 31
Jiang, Songtao 30
Jimenez, Annika 59
Jin, Ying 9
Johnson, Jim 66
Johnston, Gordon 69
Jokinen, Riku 61
Jones, Adrian 11
Jones, Keith 42
Kaduwela, Vijitha 28
Kalt, Mike 20
Karafa, Matthew 44
Karnavat, Pranav 71
Karp, Andrew 20 , 46
Kasper, Craig 65
Kastin, Matthew 9
Katare, Anurag 57
Kessler, David 54
Kezik, Julie 32 , 47
Khoo, Jonathon 48
Kiernan, Kathleen 53
Kilhullen, Michael 14 , 37
Kim, Eun 24
Kincaid, Chuck 8 , 40 , 44
King, Gary 22
King, John 65
King, Simon 17
Kishore, Rajiv 61
Klein, William 10
Kong, Louanna 14
Koo, Kai 32
Koo, Ping 17 , 43 , 48 , 52
Kromrey, Jeffrey 16 , 24 , 25
Kros, Donald 16
Krutsick, Robert 15
Kubiak, Roman 62
Kuhfeld, Warren 6 , 26
Kumar, Deva 22
Kumbhakarna, Viraj 57
Kurch, Benno 7
Ladds, John 10
Lafler, Kirk 5 , 10 , 19 , 27 , 33 , 45 ,
48 , 49 , 52 , 64
Lakkaraju, Praveen 39
LaLonde, Steven 53
Lal, Rajesh 7
Lanehart, Rheta 24
Langston, Julianna 67
Langston, Rick 20 , 49
LeBouton, Kimberly 63
Le, Binh 38
Lee, Reginald 24
Lee, Taiyeong 38
LeHong, Hung 22
Leonard, Michael 55
Leslie, Shannon 26
Levine, Fred 32
Levine, Jonathan 12
Levy, Jason 34
Lew, Robert 25
Liang, Qingfeng 42
Liao, Hsini 30
Li, Arthur 20 , 44 , 54 , 64
Li, Mei 35
Line, Stetson 65
Lin, Guixian 69
Liotus, Laura 27
Liu, Dachao 25
Liu, Hongyu 16
Liu, Jiawen 18
Liu, Shibin 13
Lohr, Sharon 71
Losh, Jason 26
Luo, Danni 57
Manickam, Airaha 19
Marianne, Estelle 62
Markey, Elaine 68
Mars, AnnMaria 40
Marson, Barry 27 , 71
Martell, Carol 7
Massengill, Darrell 67
Matange, Sanjay 39
McCormack, Don 54
McDowell, Allen 54
McQuiggan, Scott 8 , 32
Mefford, Jennifer 18
Melguizo, Maria 53
Mendicino, Thomas 71
Mendoza, George 33
Mengelbier, Magnus 41 , 57
Meng, Xiangxiang 36 , 60
Merry, Nick 62
Miclaus, Kelci 63
Middleton, Woody 66
Milbuta, Scott 49
Milhøj, Anders 55
Miller, Ethan 9
Miller, Lori 24
Milum, Jenine 18 , 35
Mooney, Stephen 59
Mott, Andrew 58
Mouton, Dwight 22
Mukhopadhyay, Pushpal 6
Mullin, Charles 45
Murphy, Matthew 18
Murphy, William 34
Murray, Maureen 50
Nadimpalli, Varma 71
Nakkeeran, Karthik 17
Na, Yingbo 60
Nelson, Gregory 5 , 7 , 11 , 58
Ngo, Theresa 53
Nguyen, Sandra 41
Nieto, Ana 12
Nijsen, Edwin 58
Nist, Pauline 22
Njuguna, Kamau 32
Nori, Murali 48
Novotny, Paul 69
Ogden, David 42
Okerson, Barbara 17
Oltsik, Myra 44
Olvera, Juan 27
Osborne, Anastasiya 21
Osborn, Natalie 28
Overton, Stephen 8 , 11 , 72
Owens, Corina 16
Pakalapati, Tathabbai 16
Palanca, Ronald 34
Palan, Urvir 61
Pande, Yogesh 9
Pantangi, Anil 62
Park, Heesun 27
Parsons, Natalie 32
Patel, Paresh 31
Pease, Andrew 64
Perry, Isabel 59
Petit-Bois, Merlande 25
Petrova, Tatyana 30
Pham, Huong 38
Pham, Thanh 25
Phillips, Jeff 67
Plaskas, Carrie 22
Plemmons, Howard 36 , 49
Polak, Leonard 9
Pool, Gary 66
Poppe, Frank 36
Poulsen, Rachel 44
Powell, Ben 65
Powell, Teresa 14
Pratt, Jesse 47
Pratt, Rob 63
Pruitt, Rex 65
Purushothaman, Ramya 15
Puttabasavaiah, Suneetha 36
Qiu, Hao 13
Rai, Kulwant 38
Raithel, Michael 42
Ramesh, Ramaswamy 42
Ranga, Raghavender 7
Ransdell, Bucky 26
Rausch, Nancy 11 , 49
Reynolds, Robbie 65
Rhoads, Michael 7
Rhodes, Dianne 65
Richardson, Kari 23 , 51 , 69
Rodriguez de Gil, Patricia 24
Rodriguez-Deniz, Hector 64
Rodriguez, Robert 49
Roehl, William 60
Roesch, Amanda 37
Rosario, Allan 18
Rosenbloom, Mary 10 , 33
Rossland, Eric 23 , 51 , 68 , 69
Roy, Ash 60
Rubendall, Craig 48
Russell, Kevin 45
Sa-Ngasoongsong, Akkarapol 55
Sabourin, Philippe 8
Sadiq, Sabah 63
Sall, John 54
Sanders, Scott 21
Sanli, Tugrul 28
Sarker, Rahman 68
Schacherer, Christopher 37 , 50
Schikore, Daniel 30
Schmiedl, Ryan 48
Schneider, Mark 26 , 48
Schubert, Sascha 38
Schultz, Stephen 62
Schulz, Falko 8 , 29
Schwartz, Theresa 24
Scroggins, Tobin 29
Secosky, Jason 43 , 48
Sempel, Hans 34
Sethi, Saratendu 39 , 49
Shah, Yogen 12
Shaik, Zubair 39
Shajenko, Lessia 40
Shakshober, Douglas 27
Shamlin, David 19 , 49
Shan, Xia 9 , 67
Shapiro, Mira 21 , 49
Sharman, Raj 42
Shipp, Charles 48 , 52 , 64
Shive, Wanda 22
Shu, Amos 59
Siddiqi, Naeem 13
Singh, Ranjit 42
Singh, Subhashree 33
Sivertson, Cheryl 31
Skoglund, Jimmy 13
Slaughter, Susan 66
Sloan, Jeff 69
Smith, Casey 50
Smith, Kevin 47
Snyder, Rita 16
Snyder, Ryan 29 , 47
Song, Ning 18
Soria, Alexander 21
So, Ying 69
Sparano, Steve 8
Srivastava, Anurag 71
Steinberg, Jonathan 56
Stephens, Robert 48
Stetz, Cynthia 47
Stewart, Larry 64
Stewart, Wesley 21
Stokes, Maura 6 , 24
Stovic, Jane 26
Stuelpner, Janet 18
Suhr, Diana 56
Sukhwani, Sumit 10
Suklani, Vikram 71
Sullivan, Linda 50
Summers, Ed 67
Suoh, Setsuo 19
Swearingen, Christopher 53
Swenson, Chris 33 , 61
Sykes, Jenn 12
Tabachneck, Arthur 9 , 10 , 65
Tabladillo, Mark 68
Tan, Angelina 69
Tao, Jill 53
Tavakoli, Abbas 16
Thangavel, Ganesh 41
Thompson, Greg 33
Thompson, Stephanie 53
Thompson, Wayne 39 , 48
Thorne, Gregory 8
Thornton, Patrick 10 , 47
Tobias, Randy 67
Tsuboi, Toshi 62
van Berkel, Anthony 13
Van den Poel, Dirk 70
VanBuskirk, Julie 67
Vanderlinden, Mike 8 , 31
Varney, Brian 31 , 32
Vaughn, Scott 22
Ventura, Audrey 44
Viergever, William 19
Villacorte, Renato 14
Vitron, Christine 23 , 51 , 69
Zhao, Wuchen 54
Zhao, Yi 46
Zhou, Jay 7
Zhu, Qiaohao 37
Wainwright-Zimmerman, Andrea
9 , 21
Waller, Jennifer 40
Wang, Chunmao 41
Wang, Wei 64
Wang, Ying 49
Wang, Zhiwei 59
Warwick, Jacob 17
Watts, Perry 21
Whitesel, Brent 57
Wicklin, Rick 6
Wilds, Fred 24
Williams, Christianna 15 , 39
Witelson, Shira 70
Wolff, Mark 42
Wong, Doris 13
Wong, JuYin 16
Wong, Rocket 41
Wu, Hongsheng 25
Wu, Yi-Fang 17
Xiao, Yang 36
Xu, Ting 13
Yang, Dongsheng 54
Yaraghi, Niam 42 , 61
York, John 13
Yuan, Yang 24
Yu, Haining 28
Yu, Hsiwei 32
Zahrn, Frederick 28
Zaratsian, Dan 13
Zeig-Owens, Rachel 24
Zender, Cynthia 5 , 20 , 43 , 45
Zeng, Zemin 35
Zhang, Guangzhi 50
Zhang, Jingxian 34
Zhang, Sijian 34
Zhang, Tony 9
Zhang, Yanwei 21
Cabana Deck &
Dolphin Pools
Get Acquainted
Lake Terrace &
Swan Pool
Opening Night
Walt Disney
World Dolphin
Walt Disney
World Swan
Join us next year as SAS Global Forum moves west to the Moscone West Center, San Francisco,
California, from April 28–May 1.
Be sure to stop by the San Francisco booth in the SAS Support & Demo Area to learn more
about this exciting destination and plans for 2013.
Rick Mitchell of WESTAT will be the 2013 Conference Chair.
(Monday and
Northern Hemisphere
B, C and D
B (Monday and
C Tuesday) D
Northern Hemisphere
Ballrooms B, C and D
C and D
(Monday and Tuesday)
and D
B, C and
Northern Hemisphere Foyer
Northern Hemisphere
Northern Hemisphere
Foyer C and D
Internet Cafe
Internet Cafe
Northern Hemisphere
Reception for
TO LOBBYInternet Cafe
Information STAIRS TO
Center LOBBY
Reception for
Reception for
Southern Hemisphere
Foyer Foyer
(Wednesday Only)
& Faculty
& Faculty
Demo Area
Demo Area
2 Only) 1
3 (Wednesday
Only) TO
Internet Cafe Porte
3 Drop
for Disney’s
Spring Resort and Gaylord
Drop Off/Pick UpTO
for Disney’s
Spring Resort and Gaylord
Palms Hotel
Book Drive
Book Drive
Hello Florida
Hello Florida
Book Drive
Meet Up
& Faculty
Hello Florida
Meet Up
Meet Up
Bus Drop Off/Pick Up
for Disney’s Coronado
Spring Resort and Gaylord
Palms Hotel
Opening Session
Kick BackSession
SAS Support and Demo Area
Mixer hosted
by SAS Customer
SAS Support
Demo Area
Tech Connection
Mixer hosted by SAS Customer Loyalty
WayFinder Kiosks
Hall Foyer
Atlantic Hall Foyer
Hall Foyer
Tech Connection
Kick Back Party
SAS Support and Demo Area
Hall Foyer
Atlantic Hall Foyer
Mixer hosted by SAS
WayFinder Kiosks
Pacific Hall Foyer
Atlantic Hall Foyer
Atlantic Hall Foyer
Was this manual useful for you? yes no
Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Download PDF