[R] Harrell's C

[Wachtel, Mitchell]

Dear Professor Harrell:

Thank you so much for your excellent advice. I just installed the proper
version of Hmisc, which works perfectly. Hmisc yields Harrell's C
(rcorr.cens); all one need do is calculate the expected value for the
risk for each patient and make that the X variable.  You are a wonderful
influence on all who perform statistics. 

With kindest regards.

Mitchell S. Wachtel, MD



-----Original Message-----
From: Frank E Harrell Jr [mailto:f.harrell at vanderbilt.edu] 
Sent: Saturday, June 02, 2007 5:01 PM
To: Wachtel, Mitchell
Cc: r-help at stat.math.ethz.ch; Thomas Dupont
Subject: Re: [R] Harrell's C

Wachtel, Mitchell wrote:
> R will not let me load Design or Hmisc anymore. I need to calculate
Harrell's C for some survival analyses. Can anyone provide an R formula
for Harrell's C?
> With kindest regards.
> Mitchell Wachtel, MD

You provided very little information.  We have had no reports of Hmisc 
not loading under Windows but Design is not currently available for 
Windows for R 2.5.  We are working to fix that.

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