On Tue, 08 Nov 2005 12:02:52 +0100, Ciro Marziliano wrote:
CM>
CM> How can I obtain the likelihood ratio of a Poisson regression
CM> model?
likelihood ratio for testing which hypothesis?
however, in GLM the deviance provides the essential ingredient
for the job, since
deviance = 2(log L(saturated model) - log L(fitted model))
best wishes
Adelchi Azzalini
--
Adelchi Azzalini <azzalini at stat.unipd.it>
Dipart.Scienze Statistiche, Universit?? di Padova, Italia
tel. +39 049 8274147, http://azzalini.stat.unipd.it/