Model Fitting: Robust Regression

Overview of the Robust Regression Analysis

The Robust Regression analysis fits a linear regression model that is robust in the presence of outliers and high leverage points. You can use robust regression to identify observations that are outliers and high leverage points. Once these observations are identified, they can be reweighted or excluded from nonrobust analyses.

You can run a Robust Regression analysis by selecting AnalysisModel FittingRobust Regression from the main menu. The computation of the robust regression function and the identification of outliers and leverage points are implemented by calling the ROBUSTREG procedure in SAS/STAT software. See the documentation for the ROBUSTREG procedure in the SAS/STAT User's Guide for additional details.