[R] output (p-values) of "fastbw" in Design package

Frank E Harrell Jr f.harrell at vanderbilt.edu
Tue Oct 27 15:08:58 CET 2009

North, Bernard V wrote:
> I am using the validate option in the Design package with the Cox survival model.
> I am using the bw=T option which, like the fastbw function, performs a backward elimination variable selection
> The output includes a series of columns (below) giving information on eliminated variables.
> My question is that I am unsure of the difference between the 2 p-values given (the one after Chi-Sq and the one after df)
> This may be a gap in my statistics knowledge, hopefully I've not asked too silly a question, many thanks in advance
>                 Backwards Step-down - Original Model
>  Deleted    Chi-Sq d.f. P      Residual d.f. P      AIC

The first chi-sq stat is the individual partial chi-sq for testing the 
deleted variable, adjusted for all variables still in the model.  The 
residual chi-sq test is the simultaneous test for all variables deleted 
up to and including the current one.


Frank E Harrell Jr   Professor and Chair           School of Medicine
                      Department of Biostatistics   Vanderbilt University

More information about the R-help mailing list