[R] Nomogram (rms) for model with shrunk coefficients

Frank Harrell f.harrell at Vanderbilt.Edu
Mon Jun 24 23:41:18 CEST 2013


You are using an informal shrinkage method.  It is much better to use 
penalized maximum likelihood estimation, built in to lrm.

If you really want to go the informal route, compute the linear 
predictor from your final estimates and use ols( ) to predict that from 
the component variables (you'll get an R^2 of 1.0 so specify sigma= to 
ols) and use nomogram on the result.

Frank


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



More information about the R-help mailing list