Dear Barry, My first guess would be to use the likelihood profile provided as an output of PGLS, and extract the (frequentists) intervals according to it. http://www.jstor.org/stable/2985006 Hope that helps, regards, Xavier
2013/6/3 Simon Blomberg <s.blombe...@uq.edu.au> > I don't know about using Caper, but you will not get "phylogenetically > independent" residuals by using the residual SSQ from the PGLS regression. > The raw residuals of a PGLS are not uncorrelated. You can get approximately > independent, uncorrelated residuals by pre-multiplying the (standardised) > residuals by the inverse square root of the phylogenetic covariance matrix. > If you use the nlme package to fit the pgls model, you can get these by > specifying type="n" in residuals.gls(). > > Note that this will not really solve your problem. The reason is that it > is hard to define what a confidence or prediction interval/band should look > like for correlated data. This is because the interval depends not only on > your explanatory variables, but also on the phylogenetic covariance of your > (unknown, unmeasured) species. > > Sometimes you will find that there are things that R won't let you do > easily because it really doesn't make much sense to do those things. > > Cheers, > > Simon. > > > On 03/06/13 17:51, Barry Lovegrove wrote: > >> Dear all, >> >> I am trying to fit 95% confidence and prediction intervals (lines) to a >> PGLS regression estimated with Pagel's ML branch length transformations for >> a regression which I calculated in Caper. I can't seem to find a routine >> for this. I can only find the param.CI command for estimating the CIs of >> the transformation parameters. To calculated intervals lines for an OLS 1 >> would use the residual sum of squares from the regression to calculate the >> lines using, for example, equations 17.26 and 17.29 in Zar (1984). If I do >> this using the RSSQ from the pgls regression will I get appropriate >> phylogenetically independent residuals? I'd be grateful for some advice. >> >> Many thanks, >> >> Barry >> >> >> Prof Barry G. Lovegrove >> School of Life Sciences >> University of KwaZulu-Natal >> P/Bag X01 Scottsville >> 3209 >> South Africa >> >> Tel: +27-33-2605113 (w) >> Tel: +27-33-3423051 (h) >> Cell: 0827810655 >> Fax: +27-33-2605105 >> >> ======= Please find our Email Disclaimer here-->: http://www.ukzn.ac.za/* >> *disclaimer <http://www.ukzn.ac.za/disclaimer> ======= >> >> [[alternative HTML version deleted]] >> >> ______________________________**_________________ >> R-sig-phylo mailing list - R-sig-phylo@r-project.org >> https://stat.ethz.ch/mailman/**listinfo/r-sig-phylo<https://stat.ethz.ch/mailman/listinfo/r-sig-phylo> >> Searchable archive at http://www.mail-archive.com/r-** >> sig-ph...@r-project.org/<http://www.mail-archive.com/r-sig-phylo@r-project.org/> >> > > > -- > Simon Blomberg, BSc (Hons), PhD, MAppStat, AStat. > Lecturer and Consultant Statistician > School of Biological Sciences > The University of Queensland > St. Lucia Queensland 4072 > Australia > T: +61 7 3365 2506 > email: S.Blomberg1_at_uq.edu.au > http://www.**evolutionarystatistics.org<http://www.evolutionarystatistics.org> > > Policies: > 1. I will NOT analyse your data for you. > 2. Your deadline is your problem. > > Statistics is the grammar of science - Karl Pearson. > > > ______________________________**_________________ > R-sig-phylo mailing list - R-sig-phylo@r-project.org > https://stat.ethz.ch/mailman/**listinfo/r-sig-phylo<https://stat.ethz.ch/mailman/listinfo/r-sig-phylo> > Searchable archive at http://www.mail-archive.com/r-** > sig-ph...@r-project.org/<http://www.mail-archive.com/r-sig-phylo@r-project.org/> > -- *--------------------------------------- Xavier Prudent * * Computational biology and evolutionary genomics * * * *Guest scientist at the Max-Planck-Institut für Physik komplexer Systeme* *(MPI-PKS)* *Noethnitzer Str. 38* *01187 Dresden * * * *Max Planck-Institute for Molecular Cell Biology and Genetics* * (MPI-CBG) * * Pfotenhauerstraße 108 * * 01307 Dresden * * * * Phone: +49 351 210-2621 * *Mail: prudent [ at ] mpi-cbg.de **---------------------------------------* [[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/
