Hi there,
I'm new to some of these more advanced regression techniques and also new to
R. This looks like a great forum.
I am trying to examine the association with membership in a group and some
different variables, most of which are (approximately) normally distributed.
Would just do an ANOVA, but I have correlated data. Everyone in my dataset
has a sibling in the sample. The correlation is a nuisance for the purpose
of what I'm interested in.
I know that some individuals have used linear mixed models and modeled the
nuisance correlation as a random effect.
My question is -- I've seen quite a few people write about using the GLM
with the "survey" package, which can apparently also handle correlated data,
and it seems like there is really detailed documentation for the package,
which is a must for me, as I'm still learning. What are the
advantages/disadvantages to using this survey package (and specifying a
normal distribution) instead of a linear mixed model package? I'm
interested in practical issues with implementation in R, as well as
statistical concerns that I should be aware of...
If LMM is better, which package to people recommend?
--
View this message in context:
http://r.789695.n4.nabble.com/Survey-package-GLM-vs-Linear-Mixed-Models-tp4636207.html
Sent from the R help mailing list archive at Nabble.com.
__
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.
