Last week I attended SAS Global Forum 2015 in Dallas. It was packed with almost 5,000 attendees. I learned many interesting things at the conference, including the fact that you need to arrive EARLY to the statistical presentations if you want to find an empty seat!

It was gratifying to see that matrix programming with SAS/IML software is alive and well in the SAS statistical community. I was impressed with the number and quality of presentations that featured SAS/IML programs. I attended the following talks or e-posters:

• "Permit Me to Permute: A Basic Introduction to Permutation Tests with SAS/IML," by John Vickery. John works in the library at NC State University and taught himself SAS/IML in order to implement a nonparametric permutation test to analyze library search engine tools. His paper is extremely well written, so check it out. It was exciting to see that Vickery's bibliography contained several references to my blog!
• "Tell Me What You Want: Conjoint Analysis Made Simple Using SAS," by Delali Agbenyegah, shows how to conduct conjoint analysis by using some of Warren Kuhfeld's market research macros.
• "How to Use SAS for GMM Logistic Regression Models for Longitudinal Data with Time-Dependent Covariates," by Katherine Cai and Jeffrey Wilson. The SAS/IML language was used for multivariate integration and for optimization.
• "SAS-PIRT (SAS macro) for Estimating Parameters of Polytomous Items Based on Graded Response Model (GRM)," by Sung-Hyuck Lee who works for ACT, Inc. As the parent of a high-school student who will soon be taking the ACT college placement test, it is thrilling to know that SAS/IML software is used to estimate the difficulty of questions on the test, which helps to differentiate students' abilities.

Of course, SAS/IML was included in my presentation Ten Tips for Simulating Data with SAS, which was very well attended. The SAS/IML language was also used in several e-posters and presentations that unfortunately I could not attend due to other commitments. All of the papers for the proceedings are available online, so you can search the proceedings for "IML" or whatever other topic interests you.

It was energizing to listen to and talk with dozens of SAS customers. The conference demonstrated that the SAS/IML language is actively used for optimization, integration, simulation, and matrix computations, which are topics that I blog about frequently. I discussed SAS/IML or general statistical topics with dozens of customers during meals, at coffee breaks, in the hallways, and in The Quad.

At the Opening Session, I learned that the free SAS University Edition has been downloaded more than 250,000 times in the 11 months that it has been available. Because SAS/IML is part of the SAS University Edition, I expect the number of SAS/IML users to continue to grow. Experienced SAS programmers recognize that when an analysis is not available in any SAS procedure, the SAS/IML language is often the best choice for implementing the algorithm.