I posted a question earlier concerning a mixed model with binomial link
for a split-plot experiment with repeated measures. The answer is the
GLMM function in the lme4 package. Now I have to fit a mixed model in
which the response variable takes the ordered values 0, 1 or 2 -
representing 0, 1 or 2 out of two marked leaves per plant that have died
at each census period in the same split-plot experiment. This response
variable should therefore follow a multinomial (3-state) distribution,
no? If so, is it possible to fit a mixed model given a multinomial
distribution? What function would I use?
The alternative is to consider a binary response (no leaves dead vs. at
least 1 leaf dead) and the GLMM function, but this would be far from
ideal. Any suggestions are welcome.
Bill Shipley
Subject Matter Editor, Ecology
North American Editor, Annals of Botany
Département de biologie, Université de Sherbrooke,
Sherbrooke (Québec) J1K 2R1 CANADA
Bill.Shipley@USherbrooke.ca
<http://callisto.si.usherb.ca:8080/bshipley/>
http://callisto.si.usherb.ca:8080/bshipley/
[[alternative HTML version deleted]]
