The ROBUSTREG Procedure

offers four estimation methods: M, LTS, S, and MM

provides 10 weight functions for M estimation

provides robust R square and deviance for all estimates

provides asymptotic covariance and confidence intervals for regression parameters by using the M, S, and MM methods

provides robust Wald and F tests for regression parameters by using the M and MM methods

provides Mahalanobis distance and robust Mahalanobis distance by using the generalized minimum covariance determinant (MCD) algorithm

provides outlier and leverage-point diagnostics

supports parallel computing for S and LTS estimates

supports constructed effects, including spline and multimember effects

produces fit plots and diagnostic plots by using ODS Graphics