R: [R] Hosmer- Lemeshow test

[Frank E Harrell Jr]

On Thu, 17 Jul 2003 16:32:05 +0200
Vito Muggeo <vito.muggeo at giustizia.it> wrote:

> As far as I know, the Hosmer-Lemeshow test is not a good choice, as it
> depends on the groups to be formed to compute the statistic.
> The design and/or hmisch  packages by F.Harrell should include some
> alternative GoF statistics, but I didn't try.

Correct.  Use the more powerful one degree of freedom test of Hosmer, le Cessie, et al:

f <- lrm( . . ., x=T, y=T)
resid(f, 'gof')

Frank

> 
> Some weeks ago there has been a similar message about GoF test with sparse
> date in logistic regression model. You could look for it and contact the
> author....
> 
> best,
> vito
> 
> 
> 
> ----- Original Message -----
> From: Andi Felber <felber at slf.ch>
> To: <r-help at stat.math.ethz.ch>
> Sent: Thursday, July 17, 2003 3:53 PM
> Subject: [R] Hosmer- Lemeshow test
> 
> 
> > dear all,
> >
> > i made some analysis with logistic regression. do you know if there is
> > already a function available for the hosmer-lemeshow fitness test?
> >
> > thank you very much for the help
> >
> > best wishes
> >
> > andi
> >
> > ______________________________________________
> > R-help at stat.math.ethz.ch mailing list
> > https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help


---
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