SAS Analytics R&D News

Summer is in full swing here in the Carolinas. Now that I have a little extra time on my hands, the backyard beer garden has never looked better. It is just way too hot and humid to enjoy it!

If you have not had time to check out the virtual SAS^® Global Forum 2020, fear not! This year’s virtual event is available on demand, so you can watch it from anywhere, anytime, and registration is free. Head over to the Quad and check out the Advanced Analytics presentations. Michael Lamm’s presentation on PROC GAMSELECT will get you started on how to do model selection with a generalized additive model.

PharmaSUG is also virtual this year. You can register for the conference and view submitted papers on the conference website. July 23 is the last day of live webinar presentations for the conference. Check out the schedule on the PharmaSUG site to see if any of the remaining presentations interest you.

We are also preparing our online presence for the Joint Statistical Meetings next month. Check out our virtual expo site to see what’s new with SAS^® analytics software and to schedule a video conference with one of our development staff.

SAS has extended its work-safer-from-home recommendation until at least September 7. The various virtual tools at our disposal, like Skype, Teams, Zoom, Webex, and even WhatsApp and FaceTime, have had the unexpected benefit of bringing me even closer to many of my coworkers, colleagues, and friends. SAS campus in Cary can be a big place. It is often not easy to schedule a face-to-face meeting with a colleague in a building half a mile away. Once we are finally back in the office, these tools that have carried me through the last four months will remain in my toolbox. While I look forward to the time when I can meet face to face with a colleague who works across campus, I will not forget that I can jump on Teams or Zoom to contact them with a more personal touch than I get with a phone call or IM.

Phil Gibbs

Manager, Advanced Analytics Technical Support

Technical Papers

Recent Developments in Survival Analysis with SAS^® Software

Survival analysis is a key technique in data-driven decision-making, which is now central to public interest because of COVID-19. Applying the correct technique for the specific question at hand is crucial for credible public health inferences. If you are interested in assessing how a risk factor or a potential treatment affects the progression of a disease—such as how long a patient takes to recover—then survival analysis techniques come into play.

Survival analysis deeply respects the ultimate source of its data, often the disease experience or even the life and death of human patients. It seeks to exploit every last drop of information that this experience can render for saving lives—in particular, not only whether patients survived, but how long, and why. And it strives to do so with minimal assumptions, so that the data are truly driving the decision.

Survival analysis has long been a strong component of SAS. But in case you’re not familiar with how it has kept up with the times, Gordon Brown provides an overview of how new SAS tools enable you to overcome a variety of new challenges, such as nonproportional hazards, interval censoring, big data, and more.

Incorporating Auxiliary Information into Your Model Using Bayesian Methods in SAS^® Econometrics

In addition to data, analysts often have at their disposal useful auxiliary information about inputs into their model—for example, knowledge that high prices typically decrease demand or that sunny weather increases outdoor mall foot traffic. If used and incorporated correctly into the analysis, the auxiliary information can significantly improve the quality of the analysis. But this information is often ignored. Bayesian analysis provides a principled means of incorporating this information into the model through the prior distribution, but it does not provide a road map for translating auxiliary information into a useful prior. Matthew Simpson reviews the basics of Bayesian analysis and provides a framework for turning auxiliary information into prior distributions for parameters in your model by using SAS Econometrics software. He discusses common pitfalls and gives several examples of how to use the framework.

Technical Highlights

Analytics R&D Director Fang K. Chen Named ASA Fellow for 2020

The American Statistical Association (ASA) bestowed the prestigious distinction of Fellow on Fang K. Chen for his professional contributions, leadership, and commitment to the field of statistical science. Fang responded: “I am honored to have been named a Fellow, to be recognized by my professional peers, and to be among the wonderfully impressive group of such honorees from SAS. All of them have done so much and have had such a great impact—it’s very humbling.” He joins the distinguished ranks of other SAS ASA Fellows, including Jim Goodnight (1981), John Sall (1998), and Randy Tobias (2009).

Upcoming Ask the Expert Free Webinars

Causal Inferences: An Introduction

Data analysts and statisticians can learn how causal inference helps explain whether results can be attributed to a particular cause in varied situations.

How Can I Run My DATA Step Programs in SAS^® Viya^®?

Learn to use all your valuable programming skills in SAS Viya.

How Do I Integrate SAS Viya and Open Source?

Use your programming skills to get the most out of SAS Viya in an open source interface that works for you.

Image Classification Using SAS

Brian Gaines demonstrates how to use a new task in SAS^® Studio to jump-start the development of SAS code to train an image classification model with the power of SAS Viya.

The DO Loop

Distinguished Research Statistician Developer Rick Wicklin introduces the iml action, which is available in SAS Viya 3.5, and offers a general method for parallel computation in SAS Viya using the MAPREDUCE function in the iml action. He also shows how to perform two-dimensional bilinear interpolation in SAS by using a SAS/IML^® function and how to estimate the difference between percentiles.

Tech Support Points Out

RunBY Macro: Add BY Processing to Macros, Procedures, or Special Code

Most SAS procedures feature a BY statement that allows the procedure to repeat its analysis or operation on each block of observations (called BY groups) found in the input data set. For example, if your data set contains a block of observations for each of several countries or regions or conditions (such as gender or race), the BY statement in most SAS procedures enables you to run the procedure a single time to obtain the results for all BY groups. However, many macros and some procedures were not written with this built-in capability. The RunBY macro emulates BY-group processing and makes it available with macros, procedures, or other SAS code. Unlike when you use the BY statement in a procedure, it is not necessary to sort the input data before using the RunBY macro. To use it, you place the code that you want to repeat in a simple macro, which the RunBY macro calls for each BY group. Although the RunBY macro can be used to add BY-group processing to your own macros or those from other SAS users, it can also be used with analytical macros such as the following:

Margins: Compute predictive margins and average marginal effects.

MAGREE: Compute estimates and tests of agreement among multiple raters.

*NLEstimate: Estimate and test nonlinear combinations of model parameters.

*NLMeans: Estimate and test differences, ratios, or contrasts of means in generalized linear models.

MultAUC: Compute the area under the ROC curve (AUC) measure for multinomial models.

RsquareV: Compute R-square statistics for generalized linear models based on the variance function.

*Marginals: Create marginal fit diagnostic plots for linear and generalized linear models.

*These are autocall macros that do not need to be downloaded and defined before use in SAS 9.4 TS1M6.

Talks and Tutorials

JSM 2020

Virtual conference, August 2−6

Finding the Source of Grandma’s Chili: Investigative Text Mining – Scott Wise

Interpolating Population Distributions Using Public-Use Data with Application to the American Community Survey − Matthew Simpson

Modern Bayesian Software: A Survey of Current Capability and Usages – Fang K. Chen

Teaching Data Science with JupyterLab – Brian Gaines

Quick Links

Statistics & Operations Research Home

Bayesian Resources

SAS Analytics: 14.3, 14.2, 14.1, and 13.2

FASTats: Frequently Asked-For Statistics

SAS/STAT Procedures A-Z

Analytical SAS Software Video Portal

SAS/STAT Example Programs

SAS/ETS Example Programs

SAS^® Statistics and Operations Research News

COMMUNITIES: SAS Statistical Procedures | SAS/IML | SAS/OR

www.sas.com | subscribe | unsubscribe

Don't miss important updates from SAS! Please add sas.com as a domain in your safe sender list.
Want to get more out of your relationship with SAS? Update your SAS profile.

About this e-mail:
If you do not wish to receive future SAS® Statistics and Operations Research News editions, please unsubscribe.
SAS places great value in fair information practices and in connection with the management of our contact database, we would like to remind you that SAS Institute Inc. may use your personal contact details for marketing purposes, as stated in its privacy policy. To contact SAS via postal mail: SAS, SAS Campus Drive, Cary NC 27513 USA. ATTN: Legal Division/Privacy Manager.

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 © SAS Institute Inc. All rights reserved.

‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌

View as a web page