Hi Nina,
Indeed. Here's a more complete version:
foo - function(x)
{
nas - is.na(x$coef)
coef - x$coef[!nas]
cnames - names(coef)
coef - matrix(rep(coef, 4), ncol = 4)
dimnames(coef) - list(cnames,
c(Estimate, S.E., t, Pr(T |t|)))
df - x$dfP - dim(coef)[1]
Hi Augusto,
I was able to reproduce some of the errors you encountered. I suggest,
if you haven't done yet, to contact directly the authors of seqinr. They
have their own mailinglist and their web site is:
http://pbil.univ-lyon1.fr/software/seqinr/
Best,
Emmanuel
Augusto Ribas wrote on
Hi Pascal,
The assumption of normality in GLS, as in OLS, concerns the residuals
not the data. A recent reference on this issue is:
Alain F. Zuur, Elena N. Ieno and Chris S. Elphick: A protocol for data
exploration to avoid common statistical problems. Methods in Ecology
Evolution 2010, 1,
I general, you should not be worrying about normality of the tip data, but
rather the residuals of whatever multiple regression-type model you are
implementing. Check those, and maybe they will be OK with a particular
combination of independent variables. Bad residuals can adversely affect
