Featured news from SAS.


View as a web page
SAS The Power to Know logo

We are just back from SAS® Global Forum in Denver, and everyone is assimilating all the customer feedback as well as working on the next release. The weather was great, and we all enjoyed our short walks from the hotels to the morning sessions, as well as lingering looks at the mountains to the west. A number of attendees and staff tacked on vacation days to their conference trip to explore said mountains.

Not me, unfortunately! But I did manage to sneak in a few innings of Colorado Rockies baseball on a break and enjoyed my first peek at the stadium (and I have to admit, watching the Red Sox scratch out a win on the American League scoreboard after being down 7–2 in the eighth inning was great fun).

But the big winners were the attendees, who saw great presentations ranging from forecasting to statistics to machine learning. And not only are SAS staff talking about SAS® Viya®, but users are now sharing their experiences, too.

You can browse the proceedings, and we highlight two of the best-attended user presentations below.

We also have the usual tips and pointers to new resources on the support site.

We head back out west in late July for the Joint Statistical Meetings in Vancouver, Canada. SAS staff are presenting four tutorials and one course. Registration begins May 1.

Here’s to spring. At least here in the eastern US, winter has been slow to let go!

Maura Stokes

Senior R&D Director, Statistical Applications


Highlighting User Papers


Prediction and Interpretation for Machine Learning Regression Methods

Dr. Richard Cutler of Utah State University may have achieved a first, generating sold-out audiences at his SAS Global Forum presentations two years in a row that resulted in encore presentations! His paper on new tools for the prediction of binary and numerical responses is a must read for those interested in understanding more about machine learning regression techniques and when to use what. Examples include the LASSO and elastic net for regularization in regression and variable selection, quantile regression for heteroscedastic data, and machine learning predictive methods such as classification and regression trees (CART), multivariate adaptive regression splines (MARS), random forests, gradient boosting machines (GBM), and support vector machines (SVM).


Forecasting the Value of Fine Wines

Dr. Joseph Breeden of Auctionforecast.com also brought in huge numbers to his talk about analyzing the price dynamics of fine wines to quantify predictive factors for investors. Brand, vintage, ratings, auction houses, bottle size, age of the wine, market trends, and more are considered in this analysis. Although data mining techniques are common in other applications, long-range forecasting requires a careful separation between current discrimination factors and long-term drivers. The models that are used are a combination of Age-Period-Cohort models and traditional scoring techniques. This study explores the ability to predict prices of infrequently traded wines by using known life-cycle and market attributes along with measures of brand and vintage value for the specific wine. This approach has direct applicability to consumer behavior in many industries; specifically, it has been used with great success in retail lending.


Cause-Specific Analysis of Competing Risks Using the PHREG Procedure

Competing-risks analysis extends the capabilities of conventional survival analysis to deal with time-to-event data that have multiple causes of failure. Two regression modeling approaches can be used: one focuses on the cumulative incidence function (CIF) from a particular cause, and the other focuses on the cause-specific hazard function. These two quantities, unlike the hazard function and the survival function in conventional survival settings, are not connected through a simple one-to-one relationship. The Fine and Gray model extends the Cox model to analyze the cumulative incidence function but is often mistakenly assumed to be the only modeling technique available. The cause-specific approach that simultaneously models all the cause-specific hazard functions offers a more natural interpretation. SAS/STAT® 14.3 includes updates to the PHREG procedure to perform the cause-specific analysis of competing risks. This paper describes how cause-specific hazard regression works and compares it to the Fine and Gray method.


Regression Model Building for Large, Complex Data with SAS Viya Procedures

Analysts who do statistical modeling, data mining, and machine learning often ask the following question: “I have hundreds of variables—even thousands. Which should I include in my regression model?” This paper describes SAS Viya procedures for building linear and logistic regression models, generalized linear models, quantile regression models, generalized additive models, and proportional hazards regression models. The paper explains how these procedures capitalize on the in-memory environment of SAS Viya, and it compares their syntax, features, and output with those of high-performance regression modeling procedures in SAS/STAT software.


SAS® Visual Forecasting: A Cloud-Based Time Series Analysis and Forecasting System

SAS Visual Forecasting, based on SAS Viya, is the next-generation SAS® product for forecasting. It provides a new resilient, distributed, scripting environment for cloud computing that provides time series analysis, automatic forecast model generation, automatic variable and event selection, and automatic model selection. SAS Visual Forecasting features a new graphical interface that is centered on the use of pipelines, a new microservices-based architecture, and a new fast, scalable, and elastic in-memory server environment based on SAS® Cloud Analytic Services (CAS). It provides end-to-end capabilities to explore and prepare data, apply various modeling strategies, compare forecasts, override statistical forecasts, and visualize results. The workflow framework for model generation and forecasting is shared with SAS® Visual Data Mining and Machine Learning and SAS® Visual Text Analytics. Forecast analysts and data scientists can also access the power of SAS Visual Forecasting through a flexible and powerful programming environment.


Navigating the Analytics Life Cycle with SAS Visual Data Mining and Machine Learning on SAS Viya

Extracting knowledge from data to enable better business decisions is not a single step. It is an iterative life cycle that incorporates data ingestion and preparation, interactive exploration, application of algorithms and techniques for gaining insight and building predictive models, and deployment of models for assessing new observations. The latest release of SAS Visual Data Mining and Machine Learning on SAS Viya accommodates each of these phases in a coordinated fashion with seamless transitions and common data usage. An intelligent process flow (pipeline) experience is provided to automatically chain together powerful machine learning methods for common tasks such as feature engineering, model training, ensembling, and model assessment and comparison. Ultimate flexibility is offered through incorporation of SAS code into the pipeline, and collaboration with teammates is accomplished using reusable nodes and pipelines. This paper provides an in-depth look at all that this solution has to offer.

Looking Beyond the Model with SAS® Simulation Studio: Data Input, Collection, and Analysis

Discrete-event simulation as a methodology is often inextricably intertwined with many other forms of analytics. Source data often must be repaired or processed before being used (indirectly or directly) to characterize variation in a simulation model. Collection of simulated data needs to coordinate with and support the evaluation of performance metrics in the model. Or it might be necessary to integrate other analytics into a simulation model to capture specific complexities in the real-world system that you are modeling. SAS® Simulation Studio is a component of SAS/OR® software that provides an interactive, graphical environment for building, running, and analyzing discrete-event simulation models. This paper illustrates how SAS Simulation Studio enables you to tackle each of these discrete-event simulation challenges.


Technical Highlights

Blog Icon

The DO Loop

Distinguished Research Statistician Developer Rick Wicklin discusses random number generators in SAS, including five new ones. You may also be interested in learning how to create a stacked band plot, which has a variety of applications in data analysis. Speaking of graphs, this zipper plot is a great way to visualize coverage probability in simulation studies.


Blog Icon

Graphically Speaking

Distinguished Research Statistician Developer Warren Kuhfeld takes on LOESS and penalized splines in a couple of blog posts this year. In addition, you can learn about using DRAW statements and then find out even more about DRAW statements for those of you looking to expand your ODS Graphics GTL knowledge.



Tech Support Points Out

Tech Support Points Out icon

Estimating the Difference in Differences of Means

A popular request lately has been for the difference in differences of means. This note discusses how to generate these measures for ordinary regression models as well as generalized linear models, for which the NLEstimate macro may be useful. 



Talks and Tutorials


JSM 2018

The following courses and tutorials are being taught at JSM this summer by SAS statistical developers:



Quick Links


SAS® Statistics and Operations Research News

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.