Penalized Regression Methods for Linear Models in SAS/STAT

Regression problems with many potential candidate predictor variables occur in a wide variety of scientific fields and business applications. These problems require you to perform statistical model selection to find an optimal model, one that is as simple as possible while still providing good predictive performance. Traditional stepwise selection methods, such as forward and backward selection, suffer from high variability and low prediction accuracy, especially when there are many predictor variables or correlated predictor variables (or both). In the last decade, the higher prediction accuracy and computational efficiency of penalized regression methods have made them an attractive alternative to traditional selection methods. This paper first provides a brief review of the LASSO, adaptive LASSO, and elastic net penalized model selection methods. Then it explains how to perform model selection by applying these techniques with the GLMSELECT procedure, which includes extensive customization options and powerful graphs for steering statistical model selection.