To: Luke Matthews
Cc: r-sig-phylo@r-project.org<mailto:r-sig-phylo@r-project.org>
Subject: Re: [R-sig-phylo] follow up for lambda transform - query: how to use
an existing covariance matrix directly in a gls procedure in R?
Hi Luke.
For a fixed value of lambda this is very easy. For this examp
Subject: Re: [R-sig-phylo] follow up for lambda transform - query: how to use
an existing covariance matrix directly in a gls procedure in R?
Hi Luke.
For a fixed value of lambda this is very easy. For this example, you
would just do:
library(ape)
data(bird.orders)
dat<-data.frame(y=rnorm(23
Hi Luke.
For a fixed value of lambda this is very easy. For this example, you
would just do:
library(ape)
data(bird.orders)
dat<-data.frame(y=rnorm(23),x=rnorm(23))
rownames(dat)<-bird.orders$tip.label
mat<-vcv(bird.orders,cor=TRUE)
# following Blomberg to here
lambda<-0.75 # for instance
fit
This question picks up on a thread from last week, copied below. I've also
been able to use the approach Simon presented so concisely with gene networks
that are not strictly bifurcating. This only allows for the Brownian model;
that is, no transforms of the entries supplied in the covariance