Hello, I am interested in performing a stepwise regression using the robust regression technique to estimate the models at each stage.
At the moment I am using the lm code and the stepAIC code to select the "best" OLS model. This final model is then re-estimated using the rlm code. I am hoping there is a better was to do this, where at each step of the "stepwise" code the robust regression technique rather than OLS is used. I realise that an AIC statistic may not be available in rlm, but some other criteria is fine. Thanks. [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.