[R] pseudo R square and/or C statistic in R logistic regression

[markleeds at verizon.net]

>From: "Wang, Xiaojing" <xiw23 at pitt.edu>
>Date: 2008/03/26 Wed AM 10:08:01 CDT
>To: "'r-help at r-project.org'" <r-help at r-project.org>
>Subject: [R] pseudo R square and/or C statistic in R logistic regression

The analogue to the regression R rsquared in a GLM 
is the deviance. I don't know what C is but hopefully someone else does and will reply. 

Also, John Fox's text, "Applied Regression Analysis, Linear Models and Related Methods" and Modern
Applied Statistics with S, by Bill Venables and Brian Ripley, both do a very nice job of covering GLM's so I would look at one of those tests for the technical details. Agresti is the supposed bible but I think those are quite sufficient.





>Dear all,
>
>I am now doing the logistic regression using R. (glm, family=binomial).  Besides the standardize summary statistics generated from R, I am also interested in some more informations concerning the model fitting / prediction etc; Particularly I am interested in "pseudo R squar" and "C statistic". I searched the R- help and could only get very limited information. (Post by  Frank Harrell  mentioning about "the somers2 or rcorr.cens functions in the Hmisc library." ) However, I tried but still could not get through it. Also I found someone mentioned about do it manually.
>
>Could someone give me a more detailed information on how I could get these two summary statistics after performed the the logistic regression using glm?
>
>
>Thank you very much.
>
>***********************************************
>Xiaojing Wang    PhD
>Research Assistant Professor, Dept. of Oral Biology
>School of Dental Medicine, University of Pittsburgh
>
>Suite 500, Bridgeside Point
>100 Technology Drive
>Pittsburgh, PA 15219
>Tel:412-648-9206  Fax:412-648-8779
>Email:xiw23 at pitt.edu
>***********************************************
>
>
>
>
>	[[alternative HTML version deleted]]
>
>______________________________________________
>R-help at r-project.org mailing list
>https://stat.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>and provide commented, minimal, self-contained, reproducible code.