 |
|
|
 |
Dear Readers »
I hope everyone had a nice break over the holidays, and the new year is beginning well. I was able to see snow in Maine and New Hampshire, and went on a hair-raising sled run with my nephew, who claims he couldn’t help our sliding and falling into the only patch of icy slush. Right.
This second newsletter puts the focus on the “OR” part of the title, including news on the latest release of SAS/OR® software and an interview with Manoj Chari, the R&D Director of Operations Research.
Many folks here are finalizing their papers for SAS® Global Forum, which is being held in Washington, DC, in March. I’ll describe a few of the presentations that may be of interest to you.
Enjoy!
Maura
P.S. All comments are welcome, particularly about the types of information you most want in this newsletter.
|
|
Interview with Manoj Chari, R&D Director of Operations Research »
SAS/OR has been a key product in SAS’ analytical offerings for years and, more recently, it’s undergone a significant growth spurt in order to stay current with recent methodological developments. Optimization techniques now play a major role in other SAS products as well, such as SAS Marketing Optimization and the SAS Revenue Optimization Suite.
Manoj Chari, Director of Operations Research R&D for SAS, graduated with a PhD in operations research from UNC at Chapel Hill. He spent 11 years teaching math and performing research at the University of Waterloo and Louisiana State University before returning to North Carolina to take a position at SAS. Read more about Chari and his group in this recent interview.
|
|
New Optimization Software in SAS® 9.2 »
As discussed in the interview with Manoj Chari, the optimization capabilities of SAS/OR have been greatly updated. These tools are much more powerful and accessible, allowing you to pursue bigger and more complex optimization models. This paper provides a nice review of the role of optimization in analytics and describes the advances recently made in SAS/OR software, especially the new OPTMODEL procedure.
|
|
SAS® Simulation Studio »
Simulation software is one of the most widely used tools in operations research, with applications in fields such as manufacturing, customer service and healthcare. It provides discrete simulation, which is used to model, study, plan and improve systems that are dominated by random events. An analytical solution is often impossible for these systems, which can be driven by complicated mathematical and logical relationships.
SAS Simulation Studio, experimental in SAS/OR 9.2, is a new Java-based application for modeling and analyzing systems through the use of discrete event simulation. Its graphical user interface requires no programming and provides a full set of tools for building, executing and analyzing the results of discrete event simulation models.
|
|
Overview of SAS® 9.2 SAS/OR® Software »
SAS/OR 9.2 continues the improvements in optimization delivered beginning with three SAS/OR 9.1.3 releases (2.1, 3.1, and 3.2), along with enhanced capabilities in project scheduling and discrete event simulation. These improvements make SAS/OR easier to use and expand the scope and scale of problems that you can address with SAS/OR. In addition, the CLP procedure, experimental in SAS/OR 9.2, solves constraint satisfaction problems through the use of constraint programming.
|
|
Generalized Additive Models with the GAM Procedure in SAS® 9.2 »
The GAM procedure had a bit of an extended experimental period as we found ourselves short of a developer for this area. However, that ended when Weijie Cai joined us, and PROC GAM became standard with the 9.2 release. Generalized linear models can be useful in finding predictor-response relationships in many data situations without specifying a specific model. They allow you to explore simultaneously many nonparametric relationships with the distributional flexibility of generalized linear models. This paper describes these models and discusses an example of fitting generalized additive models with the GAM procedure. ODS graphics produce plots of integrated additive and smoothing components.
“I am very pleased with the user reaction to the new features in PROC GAM, such as fast approximate analysis of deviance and enhanced ODS graphics,” says Cai. “I hope to get additional input as I continue to work on software in this area.”
|
|
Updates to SAS® Power and Sample Size Software in SAS/STAT® 9.2 »
SAS/STAT software includes an interface for power and sample size computations called PSS. First available in release 9.1.3, this client application has been completely rewritten as a Java application for SAS 9.2. It provides convenient access to many of the power and sample size computations available through the GLMPOWER and POWER procedures. This new interface also provides access to some of the new features of the procedures, including analyses for the confidence interval of a binary proportion, power analysis for certain cases of logistic regression, analyses for two-sided equivalence tests for a binomial proportion, and the Wilcoxon Mann-Whitney test for two independent groups.
|
|
Note to SAS/STAT® PROC QUANTREG Users in Release 9.1.3 »
In one of those unfortunate things that happen, a die date was set inadvertently in the QUANTREG download executable, and this software expired on Dec. 31, 2008. To continue using this procedure with SAS 9.1.3, you will need to download an updated version. Sorry for the inconvenience.
|
|
More Web Examples for SAS/STAT® Software »
We’ve been busy working on new examples for the experimental MCMC procedure for Bayesian analysis. They now include an example using standardized covariates in linear regression and another one on missing data models.
Keep checking back as we’re steadily building this library.
|
|
Scoring with Fitted Models »
In each newsletter, SAS Statistical Technical Support points out an aspect of using SAS software that may make life a little easier for you. Many SAS Notes are rich nuggets of information. This particular note illustrates how to use fitted models to get predicted values for new values, as well as how to score a validation data set. Several procedures are discussed, and PROC GENMOD is used in the example.
|
|
This time of year, we’re looking forward to the upcoming SAS Global Forum to be held in Washington, DC, March 22-25.
R&D statistical developers are again presenting tutorials on Sunday morning. These two-hour presentations provide methodology review as well as illustrations using SAS software.
Here’s the lineup for 2009:
Introduction to Bayesian Analysis Using SAS Software: Maura Stokes
Introduction to Logistic Regression: Bob Derr
Analyzing Survey Data Using Replication Methods in SAS Software: Anthony An
Creating Statistical Graphics with ODS in SAS 9.2: Bob Rodriguez
Our invited statistical talks include ones on group sequential analysis, Bayesian analysis, and megamodel selection using SAS/STAT procedures. Both OR developers and users will be presenting in a SAS-sponsored Operations Research section.
Besides numerous SAS Presents papers, check out the Super Demos – scheduled 15-minute talks on the exhibition floor, including one on the upcoming R interface in SAS/IML® Studio.
The SAS Global Forum program is now online so you can preview all of the presentations.
Hope to see you there.
|
|
Contact Us
Have a question, comment or suggestion? Want to see something covered in the next SAS Statistics and Operations News? Simply e-mail the editor. |
| |
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. Other brand and product names are trademarks of their respective companies. Copyright © 2009 SAS Institute Inc. All rights reserved
Tech Support | Privacy Statement |
|
