Hello again,

I think the problem has to do with one extinct taxa in my tree. When I
change the branch length so the species becomes "alive" (ultrametric tree)
the abline shows up at a more "normal" place. Any hint on how I can correct
this? Maybe the only solution is to take the problematic taxon out of the
analysis...
ᐧ

2015-07-22 15:07 GMT+01:00 Sergio Ferreira Cardoso <
[email protected]>:

> Dear all,
>
> I'm analysing a small data set consisting of values for 27 taxa. I am
> extracting phylogenetic residuals from a regression (as in Revell, 2009) to
> be used as size corrected values. Almost all the residuals are negative
> because the regression line is positioned above what I would expect. Do you
> think this has something to do with the phylogeny? It probably has because
> everything looks fine with the ordinary least-squares.
> Thanks in advance.
>
> All the best,
> Sérgio.
>
> Here is the coding I used:
>
> ## Used packages
>
> > library("ape", lib.loc="~/R/win-library/3.1")
> > library("caper", lib.loc="~/R/win-library/3.1")
> > library("nlme", lib.loc="~/R/win-library/3.1")
> > library("phytools", lib.loc="~/R/win-library/3.1")
> > library("phangorn", lib.loc="~/R/win-library/3.1")
>
> ## fitting PGLS
>
> > fit_brain<-pgls(perimeter~brain,comparative.data(tree,df,"Species"))
> > summary(fit_brain)
>
> ## cross checking using phytools
>
> > phyl.resid(tree,brain,perimeter,method="BM")
>
> ## quick plotting
>
> > plot(brain,perimeter)
> > abline(fit_brain)
> > ols<-lm(perimeter~brain,data=df)
> > abline(ols)
>
>
> --
> Com os melhores cumprimentos,
> Sérgio Ferreira Cardoso.
>
> --------------------
>
> Best regards,
> Sérgio Ferreira Cardoso
>
>
>
>
> MSc. Paleontology candidate
> Departamento de Ciências da Terra - FCT /Universidade Nova de Lisboa
> Geociências - Universidade de Évora
>
> Lisboa, Portugal
>



-- 
Com os melhores cumprimentos,
Sérgio Ferreira Cardoso.

--------------------

Best regards,
Sérgio Ferreira Cardoso




MSc. Paleontology candidate
Departamento de Ciências da Terra - FCT /Universidade Nova de Lisboa
Geociências - Universidade de Évora

Lisboa, Portugal
_______________________________________________
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