Hi everyone,
I'm asked to perform a heteroskedasticity test for a model,
Usually, I use lmtest:bptest and it works fine,
But this model I have to test was estimated using nlme:lme, and the bptest
function seems to complain about it (no R-Squared I guess?),
So I wonder: Does it exist a bptest for mixed models (or is it only
available with OLS estimated models) ?
Pinheiro and Bates only perform a graphical test in their book, then
correct the VarCov matrix, and test wether the new model significantly
improves the uncorrected one. Is it the only way to go?
Thanks for any inputs,
Sÿlv
[[alternative HTML version deleted]]
______________________________________________
R-help@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.
