fitBayes: Evolutionary model fitting with intraspecific variability using Bayesian MCMC

Description

This function uses Bayesian MCMC to sample terminal states (species means) as well as evolutionary parameters.

Usage

fitBayes(tree, x, ngen=10000, model="BM", method="reduced", control=list())

Value

An object of class "fitBayes" that includes a matrix (mcmc) with a number of rows ngen/control$sample+1 containing the posterior sample and likelihoods. Matrix columns are labeled by species (for species means and variances), or by the corresponding evolutionary parameter.

Arguments

tree: an object of class "phylo".
x: a vector of phenotypic values for individuals; names(x) should contain the species names (not individual IDs).
ngen: a integer indicating the number of generations for the MCMC.
model: an evolutionary model: either "BM" or "lambda".
method: a method: either "reduced" or "full".
control: a list of control parameters containing the following elements: sig2: starting value for $\sigma^2$ (BM rate); lambda: starting value for the $\lambda$ parameter; a: starting for the state at the root node; xbar: starting values for the states at the tips; intV: starting value for the intraspecific variance (reduced method); or v: starting value for the vector of intraspecific variances for all species (full method); pr.mean: means for the prior distributions in the following order - sig2, lambda (if applicable), a, xbar, intV or v (if applicable), note that the prior probability distribution is exponential for sig2 and normal for a and y; pr.var: variances on the prior distributions, same order as pr.mean.

Author

Liam Revell liam.revell@umb.edu

References

Revell, L. J. (2012) phytools: An R package for phylogenetic comparative biology (and other things). Methods Ecol. Evol., 3, 217-223.