s-news
[Top] [All Lists]

Re: Hey,

To: Alex Asiimwe <Alex.Asiimwe@port.ac.uk>
Subject: Re: Hey,
From: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 11 Jan 2007 10:33:29 -0600
Cc: s-news@lists.biostat.wustl.edu
In-reply-to: <45A65BD9.DA93.00D4.3@port.ac.uk>
References: <45A65BD9.DA93.00D4.3@port.ac.uk>
User-agent: Icedove 1.5.0.7 (X11/20061013)
Alex Asiimwe wrote:
Hey,
I ve used Cox regression to develop a model for prediction. However, I
would also want to calculate the AUC or ROC. How do I go about? Its is
easy when using logistic regression but I am using Cox regression.
Thanks
Alex
--------------------------------------------------------------------
This message was distributed by s-news@lists.biostat.wustl.edu.  To
unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
the BODY of the message:  unsubscribe s-news


In the Design library see the documentation for validate.cph, and in the Hmisc library see the rcorr.cens function. Generalized ROC area C and Somers' Dxy rank correlation are related by Dxy=2(C-.5).

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

<Prev in Thread] Current Thread [Next in Thread>
  • Hey,, Alex Asiimwe
    • Re: Hey,, Frank E Harrell Jr <=