Hi friends,
I need some help regarding generalized linear mixed model of unbalanced
data.
1. Is their any package for applying Monte-Carlo Newton-Raphson (MCNR) or
Monte-Carlo EM (MCEM) to estimate fixed and random effects?
2. My data is unbalanced (groups having unequal number of observations) and
random-effect design matrix is not containing only 1's but some function of
x(predictors). e.g.,
z =
[avg(x1jk) 0 0 0 0 0
0 avg(x2jk) 0 0 0 0
... ... ... ... ... ...
0 0 0 0 0 avg(x6jk)]
where avg(xijk) = an (n_k X 1) column vector of average of jth measurement
available for the ith subject in group k and n_k is the no. of observations
in kth group.
is it possible to apply glmmPQL or any other packge in this situation? If
possible kindly tell me how?
Thanks in advance.
Waiting for reply.
--
View this message in context:
http://www.nabble.com/GLMM-for-unbalanced-data-tf3762358.html#a10635105
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
R-help@stat.math.ethz.ch 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.
