Dear all,

As a newcomer in R I am playing around with CAPER and R to understand how
it works,
while testing for the correlation between discrete traits (t1, t2, t3) for
10 species:

s t1 t2 t3
s1 0 1 0
s2 0 0 0
s3 1 0 1
s4 0 0 0
s5 1 0 1
s6 0 0 0
s7 0 1 0
s8 1 0 1
s9 0 1 0
s10 1 1 1

(you may notice that t3=t1 in that exemple), I got an error message from
'brunch'

> mod = brunch(t1~t2, cd)
Error in brunch(t1 ~ t2, cd) : No factors specified in the model formula
> mod = crunch(t1~t2, cd)

and just tried 'crunch' by curiosity. Even though these variables are
binary, I obtained exactly the same result as with GLS.
That is extremely puzzling as I expected crunch to work only for binaries,
and if these results were wrong, then it would mean the GLS's one are wrong
also...

you can have a look at my code there:
http://iktp.tu-dresden.de/~prudent/Divers/R/toy.R

with the tree structure:
http://iktp.tu-dresden.de/~prudent/Divers/R/toy3.tree

Thanks in advance,

regards,

Xavier Prudent

        [[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