[R] classification table in logistic regression

[Frank E Harrell Jr]

There are many reasons not to derive a classification table.  Just to mention a few: the proportion classified correctly is highly arbitrary (depends on an arbitrary cutoff) and is an improper scoring rule (is not optimized when the model estimates the true probabilities of events); the proportion classified correctly can decrease when an important variable is added to the model.  It is also wasteful of statistical information.

When I wrote the CTABLE option for the old SAS PROC LOGIST in 1980 I later came to regret implementing it.

Frank Harrell

On Wed, 4 Sep 2002 17:44:11 +0300 (EEST)
idimakos at upatras.gr wrote:

> Friends,
> 
> Is there an option (or options) to produce a classification table when
> running a logistic regression analysis?  Similar to the ctable option in
> proc logistic in SAS?
> 
> TIA,
> 
> Ioannis
> 
> 
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._


-- 
Frank E Harrell Jr              Prof. of Biostatistics & Statistics
Div. of Biostatistics & Epidem. Dept. of Health Evaluation Sciences
U. Virginia School of Medicine  http://hesweb1.med.virginia.edu/biostat
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._