[R-sig-ME] Ordinal categorical variable as a random effect in MCMCglmm

Manabu Sakamoto manabu.sakamoto at gmail.com
Wed Oct 29 12:16:48 CET 2014

Dear list,

I'm using MCMCglmm with some random effects, including a phylogeny and a
categorical variable, scored along an ordinal scale, e.g., 1 < 2 < 3 <...

If my phylogenetic tip names are stored as a character string Taxon (and
there is an associated inverse A object), and my quality codes are stored
as an ordered factor variable Quality, then my questions are:

1) Can I specify the random effect formula simply as: random= ~ Taxon +
Quality --- i.e., without functions like us() or idh() around Quality?
2) What sort of prior should I assign for Quality? --- For the moment I am

list(V=1, nu=1, alpha.mu = 0, alpha.V = 25^2)

I'd appreciate any advise.

Kind regards.
Manabu Sakamoto, PhD
manabu.sakamoto at gmail.com

	[[alternative HTML version deleted]]

More information about the R-sig-mixed-models mailing list