Re: [R-sig-phylo] combined CI across trees (Krzysztof Bartoszek)

Hi, Another way of constructing CIs across trees is to assume a tree model and then integrate over all trees. We (with Serik Sagitov) have done this for the primary optimum parameter in the OU (paper still under review) : Krzysztof Bartoszek, Serik Sagitov Phylogenetic confidence intervals for th

Re: [R-sig-phylo] off-diagonal parameters in multivariate ouch (Krzysztof Bartoszek)

Hi Chad, I would also follow Aaron in asking why you want a particular number? You might want to take a look at the paper I co-authered : Krzysztof Bartoszek, Jason Pienaar, Petter Mostad, Staffan Andersson and Thomas F. Hansen, A phylogenetic comparative method for studying multivariate adaptati

Re: [R-sig-phylo] Fit BM, OU (1 theta), OU (2 theta) with the same function

Dear Santiago, To add to what Brian wrote there is also the mvSLOUCH package on CRAN - a multivariate generalization of slouch. It allows of course for also a univariate analysis. It also allows for a multi/univariate OU analysis. In all OU cases you can have multiple thetas on the tree. Hope th

Re: [R-sig-phylo] trait simulation function (Krzysztof Bartoszek)

Hi Gabriela! You can also use the mvSLOUCH package ( http://cran.r-project.org/web/packages/mvSLOUCH/ ) and the functions : simulBMProcPhylTree simulMVSLOUCHProcPhylTree simulOUCHProcPhylTree You probably will want the first function which is for the Brownian Motion process. Best wishes Krzy

Re: [R-sig-phylo] phylogenetic multiple regression of plant growth

Hi Dan, You might be interested in looking at my package mvSLOUCH ( http://cran.r-project.org/web/packages/mvSLOUCH/ ) and the paper : Krzysztof Bartoszek, Jason Pienaar, Petter Mostad, Staffan Andersson and Thomas F. Hansen, A phylogenetic comparative method for studying multivariate adaptation

Re: [R-sig-phylo] simulating multiple continuous traits using geiger

Dear Kasper, Comparing simulated and real data always gives you some understanding of the dynamics, however a test on the equality of distributions (Kolmogorov–Smirnov, Shapiro–Wilk) would be interesting to employ, However you would first need to make your data independent (by multypling the da

Re: [R-sig-phylo] multiple traits measured within species and populations (Krzysztof Bartoszek)

Hi Jorge! Since you use polytomies to represent your different populations then your different populations are conceptually the same as different species. If you can assume that there was no interaction between the different populations since the divergence point of the polytomy then I see no (s

Re: [R-sig-phylo] Simulate multivariate OU process

Hi Daniel, >From your description the functions simulOUCHProcPhylTree() and >simulMVSLOUCHProcPhylTree() do what you write about - they simulate multivariate OU processes and you may paint the regimes on the tree however you like. In your case - you have one global regime with different values f

Re: [R-sig-phylo] Off-diagonal elements in multivariate OU evolution (Krzysztof Bartoszek)

Hi Aaron, Cody and Julien! Cody I agree with Julien that you are mainly interested in whether the off-diagonals in A are zero or non-zero. The off diagonals in sigma would mean there is correlation but due to strange effects. You should also try with triangular A matrices - i.e. you may have ad

Re: [R-sig-phylo] Constraining node values in an OUCH analysis (Aaron King)Re: Constraining node values in an OUCH analysis (Krzysztof Bartoszek)

Hi Nathan, A bit late answer due to vacation but you can also try to use my mvSLOUCH package (on CRAN). While it (still) does not allow for explicit fossil species you can a very short tip branch at the place where the fossil should be. For missing observations you write NAs, the package has no

Re: [R-sig-phylo] Question on pCCA (phyl.cca)

Hi Sandra, Julien and Liam! One thought that I had is since you have an environmental variable and one supposedly correlated with it is that then the slouch/mvSLOUCH (on CRAN) models could be a possibility? In them you can have the environmental variable(s) evolving as a Brownian motion (i.e. ra

Re: [R-sig-phylo] Question on pCCA (phyl.cca)

Hi Julien, You are right that power is a big (and generally still unexplored in the PCM context) issue. One way to address the question is after estimating the parameters of the BM/OU/mvSLOUCH model you can calculate the covariance/correlation function of the traits, say Cov(Y)(t)/Corr(Y)(t) w

Re: [R-sig-phylo] Implementation of Mir et al.'s (2013) tree balance index

Hi Gabriel, I did some work in that direction but it is not out on CRAN yet. PM me (bartosze...@gmail.com or krzysztofbartos...@wp.pl) what you need and I'll provide you with code if I have it. Cheers Krzysztof ___ R-sig-phylo mailing list - R-sig-phy

Re: [R-sig-phylo] Using compar.gee on dataframes with multiples of the same species

Dear Skylar, The data you have fit into the framework of PCMs with measurement error that we desribed in T. F. Hansen and K. Bartoszek. "Interpreting the evolutionary regression: the interplay between observational and biological errors in phylogenetic comparative studies". In: Systematic Biolog

[R-sig-phylo] PhD positions in Evolutionay Biology with a focus on phylogenetic comparative methods

Dear all, Please feel free to spread around if you think anyone might be interested: Thank you Best wishes Krzysztof Bartoszek Ph.D. opportunity in plant evolutionary biology Nicolaus Copernicus University, Torun, Poland The Chair of Ecology and Environment Protection (http://www.keib.umk.pl/?la

[R-sig-phylo] PhD position in evolutionary biology

Dear all, If you know of anybody that could be interested in the below position please forward it to them. Best wishes Krzysztof Bartoszek Ph.D. opportunity in plant evolutionary biology Nicolaus Copernicus University, Torun, Poland The Chair of Ecology and Environment Protection (http://www.

[R-sig-phylo] quantitative state dependent diversification of another quantitative trait (Zach Culumber)

Dear Zach, You can also have a look at mvSLOUCH (on CRAN). If you have only two traits it will be similar to SLOUCH and mvMORPH (maybe mvSLOUCH will have more detailed output). But mvSLOUCH will also allow you to model multiple correlated traits responding to (multiple correlated) BM traits. Be

[R-sig-phylo] Open PhD position

Hello all, At the Division of Statistics and Machine Learning, Department of Computer Science, Linkoping University we have opened a PhD student in Statistics position that is related to phylogenetic comparative methods : liu.se liu.se www.ida.liu.se www.ida.liu.se Please feel free to sprea

[R-sig-phylo] new PCM packages

Dear all, I wanted to let you know about four PCM packages that have become available on (3 on CRAN and 1 on GitHub) recently that hopefully will be interesting to somebody. 1) There is a new version of mvSLOUCH available. The most important change is that the inference engine has been compl

Re: [R-sig-phylo] model averaging using brownie.lite

Dear Karla, Concerning the n that should be passed to AICc I agree with what was previously written that this is a complex, case by case issue. One can have a number of ways to define what could be used in place of n. However, at least in the one dimensional, BM and OU for me it seems that if

[R-sig-phylo] Stochastic differential equations with R school at Linkoping University, Sweden

Dear all, At the Division of Statistics and Machine Learning, Department of Computer and Information Science, Linköping University, Sweden, 14th-19th May 2020, we will be hosting a school concerning stochastic differential equations and the YUIMA R package (Simulation and Inference for SDEs an