Thanks Liam, it was very helpful!
Now, I am able to run the analysis by your way. However, now arises another
question:
Looking the multiPhylo structure, I tried to run the analyses in a
looping format, in this way:
analysis - NULL
for (i in 1:100 ) {
analysis[i] - aov.phylo(x~y,trees[[(i)]], nsim=100)
}
The p values are presented in console, but I did not found a way to bring
this into an object (below one of my attempts). I tried to recover the p
value inside de loop, but when the loop ends, the stored p values are all
the same (probably the p value of the last run of the loop).
for (i in 1:5 ) {
analysis[i] - aov.phylo(x~y,trees[[(i)]], nsim=100)
p.value[i]-attr(analysis, summary)$ Pr(phy)[1]
}
Thanks again for your help,
All the best,
- - Carlos
On Tue, Mar 17, 2015 at 10:55 AM, Liam J. Revell liam.rev...@umb.edu
wrote:
Hi Carlos.
If you read in a set of trees they will be stored as an object of class
multiPhylo which is a list of trees in memory.
To iterate aov.phylo across all the trees in this object (let's say,
trees), you could do the following (modifying variable names as
appropriate):
fits-lapply(trees,aov.phylo,formula=y~x,nsim=100)
Then to pull out the 'phylogenetic p-values' only in a vector you could do:
Pr.phy-sapply(fits,function(x) attr(x,summary)$Pr(phy)[1])
All the best, Liam
Liam J. Revell, Assistant Professor of Biology
University of Massachusetts Boston
web: http://faculty.umb.edu/liam.revell/
email: liam.rev...@umb.edu
blog: http://blog.phytools.org
On 3/16/2015 5:29 PM, Carlos H. Biagolini Junior wrote:
Hello, I would like to ask for an advice:
I am using the function aov.phylo () in Geiger package (Garland, 1993), to
run a phylogenetic ANOVA. I have had collected data in literature, and I
am using trees from the birdtree.org web site (for bird phylogenies).
My difficulty is: How can I perform a sequence of ANOVAs using my dataset
and the list of phylogenetic trees.
I aim to get each tree inside this list, and write a looping to run the
phylogenetic ANOVA, and store the results (i.e. p value) in an object.
However, I did not realize how can I systematically capture each tree in
this list (since the name of the trees follows a random number sequence,
i.e., within the file has trees with name: tree_3937, tree_2141,
tree_8734,
etc...).
Thanks
- Carlos Biagolini
Following my script (for now):
library(geiger)
setwd(D:/...)
# Introducing the trees
all.trees-read.nexus(mytreefile.tre) # input the 100 trees
single.tree- all.trees$ tree_3937 # one tree inside the list
# Creating a simulated dataset for exemplify
matrix- matrix(rnorm (65, mean = 0.5, sd = 0.1),nrow=65,ncol=1)
species- single.tree$tip.label # Carrying all species names for an object
rownames(matrix)-species # Naming each data
group -as.factor(rep(c(A,B,C,D,E),each=13)) ;
d1 - matrix[,1] ;
names(group) - rownames(matrix);
# Phylogenetical ANOVA
aov.phylo(d1~group, single.tree, nsim=1000)
___
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-ph...@r-project.org/
--
Carlos Biagolini-Jr
Universidade Federal de S�o Carlos
http://lattes.cnpq.br/4086237188108947
[[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/
