On Mar 4, 2012, at 12:21 , Dunia Scheid wrote:
> Dear all,
>
> I am fitting a GLM similar to
>
> library(MASS)
> anorex.1 <- glm(Treat~Postwt+Prewt,family = binomial, data = anorexia)
I hope that's just for an example. The actual analysis makes zero sense to
me...
>
> I have found two ways of computing the p-value of the fitted model:
> pval1 <- 1-pchisq(anorex.1$deviance,anorex.1$df.residual)
> pval2 <- 1-pchisq(anorex.1$null.deviance - anorex.1$deviance,
> anorex.1$df.null - anorex.1$df.residual)
>
> pval2 is testing LR chi2 from the null model, but what does pval1 says?
Not much in binary logistic regression. If you have binomial data with np > 5
in all cells, it is a goodness of fit test -- LR comparison to saturated model.
(If n=1 it can be shown to be a function of the parameter estimates, so pretty
useless as a model test.)
>
> Many thanks in advance,
> Dunia
>
> [[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.
--
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com