I have fitted a model using gee and would like to do some regression
diagnostics. The model is quite simple, three predictors, gaussian errors,
29 clusters each with 3 observations and unstructured or autoregressive
corstr give similar results.
Does anyone have any pointers to what sort of diagnostics should be
considered or some R code for this sort of thing?
I didn't find anything in recent mail archives, but did see a few people
using geese from geepack instead of gee. A look at the manual for geepack
didn't give me any leads on diagnostics though.
David Scott
_________________________________________________________________
David Scott Department of Statistics, Tamaki Campus
The University of Auckland, PB 92019
Auckland NEW ZEALAND
Phone: +64 9 373 7599 ext 86830 Fax: +64 9 373 7000
Email: d.scott at auckland.ac.nz
Graduate Officer, Department of Statistics
Webmaster, New Zealand Statistical Association:
http://www.stat.auckland.ac.nz/nzsa/