Hi, everybody
I’m trying to fit a phylogenetic model to model the relationship between x
and y (eg. lmer syntax: y~x +(1|species), species with their respective
var-covar matrix). Given that species are grouped into major categories
(families, orders, etc), What is the correct way to account for this
hierarchical structure, while estimating slopes and random intercepts for
one of those categories? For example, if I want the estimates of slopes and
intercepts for each level of the family category: what is the correct way?
a) y~x+(1|species)+(1+x|family), ## varying intercept-slope by family
(family added as another random effect),
b) y~x+(1+x|family/species) ## varying intercept-slope by family,
accounting for the fact that species are grouped into family,
or simply I have to add the family category as a fixed effect:
c) y~x+family+(1+family|species)
Best,
--
Oscar
[[alternative HTML version deleted]]
_______________________________________________
R-sig-phylo mailing list - R-sig-phylo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-phylo@r-project.org/
