Hi everyone,

I'd like to get some opinions on why estimates of Bloomberg's k are
different using the packages ape and caper in R.

Please see the code below for example, in which I used the same data but
got different estimates of k. In my own data, the estimated ks were
completely opposite: k=0.0001 in ape, and k=3 in caper.

library(ape)
library(caper)
library(nlme)
data(shorebird)

# CAPER
compdata <- comparative.data(shorebird.tree, shorebird.data, names.col =
"Species", vcv.dim=3, vcv = TRUE)

caper.model <- pgls(log(Egg.Mass) ~ log(M.Mass) * log(F.Mass), compdata,
kappa="ML")

summary(caper.model) # k=0.474

# APE
gls.model  = gls(log(Egg.Mass) ~ log(M.Mass) * log(F.Mass),
correlation=corBlomberg(value = 0.1, phy=shorebird.tree),
data=shorebird.data, method="ML")

summary(gls.model) # k = 0.9079989

Cheers,
Solomon Chak
[email protected]
Virginia Institute of Marine Science
College of William and Mary

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-phylo mailing list - [email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/[email protected]/

Reply via email to