Perhaps it is much easier to show by means of a simulation that using p-value based selection causes upward bias in regression coefficient estimates as the ones that are relatively low are less likely to be included. Ewout Steyerberg has performed many of these simulations, perhaps some code of it is available on his website: http://www.clinicalpredictionmodels.org/doku.php?id=rcode_and_data:start
Kind regards, Sander On Tue, Oct 2, 2018 at 5:54 PM R. Mark Sharp <rmsh...@me.com> wrote: > I am developing a short presentation for people with applied statistical > backgrounds who have used backward stepwise variable selection where they > remove variables based on small coefficient values, coefficient P values > > 0.05, and large variances. > > I am wanting to provide some demonstration code in R that highlights some > of the weakness as described by Frank Harrell (citation below). > > Of particular interest are (1) failure to include informative predictor > variables (categorical and continuous) and (2) lowered standard errors for > the coefficients in the final model. I have code to demonstrate inclusion > of too many false predictors. > > I expect this code is available, but I have not found it. Guidance would > be appreciated. > > Mark > P.S. I have started a public github package at > https://github.com/rmsharp/stepwiser > I has very little in it thus far. > > > Frank E. Harrell. Regression Modeling Strategies with applications to > linear models, logistic regression, and survival analysis, Springer Series > in Statistics. Springer-Verlag. 2015. > > > R. Mark Sharp, Ph.D. > Data Scientist and Biomedical Statistical Consultant > 7526 Meadow Green St. > San Antonio, TX 78251 > mobile: 210-218-2868 > rmsh...@me.com > > _______________________________________________ > R-sig-teaching@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-sig-teaching > [[alternative HTML version deleted]] _______________________________________________ R-sig-teaching@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-teaching
