Re: ROC curves

[Frank E Harrell Jr <f.harrell@vanderbilt.edu>]

asanquer@virbac.fr wrote:
> Hello,
>
> does anyone know a S function which permitted to calculate the area 
> under a ROC curve, as well as its standard error estimate ?
> thanks for your help.
>
> Annaële Sanquer
> asansuer@virbac.fr
library(Hmisc)
rcorr.cens(prediction, outcome)

This gives you Somers' Dxy rank correlation between prediction and 
binary outcome and its standard error.  Dxy = 2*(C-.5) where C is the 
ROC area or concordance probability.
--
Frank E Harrell Jr   Professor and Chair           School of Medicine
                     Department of Biostatistics   Vanderbilt University