R help - May 2007 - AIC for lrm(Hmisc/Design) model.

Um texto embutido e sem conjunto de caracteres especificado associado...
Nome: n?o dispon?vel
Url:
https://stat.ethz.ch/pipermail/r-help/attachments/20070529/6d1ea6a2/attachment.pl

Milton Cezar Ribeiro wrote:
> Dear all,
> 
> I am adjusting a Logistic Regression Model using lmr() function of
Hmisc/Design package. Now I would like to compute AIC for this model. How can I
do that?
> 
> Kind regards,
> 
> miltinho
> Brazil
I like to change AIC to have it on the chi-square scale.  For that you 
can do

aic <- function(fit)
   round(unname(fit$stats['Model L.R.'] -
2*fit$stats['d.f.']),2)

f <- lrm( )
aic(f)

If unname doesn't exist in S-Plus as it does in R, you can remove that part.

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