Hi, Rafael.
It applies for the simple OU model. Relevant code in OUwie:
if (model == "OU1"){
np=2
index<-matrix(TRUE,2,k)
index.mat[1,1:k]<-1
index.mat[2,1:k]<-2
if(root.station==TRUE){
param.count<-np+1
}
if(root.station==FALSE){
param.count<-np+2
}
bool=root.station
}
If root stationarity is assumed, there are three parameters: alpha and
sigma.sq (the np=2 cost) and theta (the +1 for param.count); if not
assumed, there is +2 for the param.count for theta at root and theta
elsewhere. For BM1, np is 1 (sigma.sq) and param.count is 2 (root state,
though the MLE for this does not require optimization as there's an
equation for it), so they should be comparable.
Best,
Brian
_______________________________________________________________________
Brian O'Meara, http://brianomeara.info, especially Calendar
<http://brianomeara.info/calendar.html>, CV
<http://brianomeara.info/cv.html>, and Feedback
<http://brianomeara.info/feedback.html>
Professor, Dept. of Ecology & Evolutionary Biology, UT Knoxville
Associate Head, Dept. of Ecology & Evolutionary Biology, UT Knoxville
He/Him/His
On Tue, Aug 27, 2019 at 12:24 PM Rafael S Marcondes <raf.marcon...@gmail.com>
wrote:
> Hi all,
>
> I'm trying to understand the number of parameters in simple BM and OU
> models in OUwie. $param.count in the fitted results gives 2 for BM and 3
> for OU. I know that the 2 BM params are sigma and the trait value at the
> root, but I'm a little confused about the OU params. I expected there to be
> 4 of them: sigma, alpha, theta and the trait value at the root.
>
> Digging a little deeper, the OUwie documentation explains that under the
> default settings (which I used), the value at the root is dropped from the
> model and drawn from the stationary distribution of the OU process. But the
> documentation only says that explicitly for the more complex OUMV and OUMVA
> models. So I just wanted to make sure that that is also applied to the
> simple OU model.
>
> I'm also wondering about the implications of this for comparing the fits of
> OU and BM, if for one (BM) the root value is estimated and for the other
> (OU) it is not...
>
> Thanks in advance,
>
>
> *--*
> *Rafael Sobral Marcondes*
> PhD Candidate (Systematics, Ecology and Evolution/Ornithology)
>
> Museum of Natural Science <http://www.lsu.edu/mns/>
> Louisiana State University
> 119 Foster Hall
> Baton Rouge, LA 70803, USA
>
> <http://goog_27804804>
> www.rafaelmarcondes.com
>
> [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-phylo mailing list - R-sig-phylo@r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
> Searchable archive at
> http://www.mail-archive.com/r-sig-phylo@r-project.org/
>
[[alternative HTML version deleted]]
_______________________________________________
R-sig-phylo mailing list - R-sig-phylo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-phylo@r-project.org/
