Monte Carlo based model choice for applied phylogenetics of continuous traits. Method described in Carl Boettiger, Graham Coop, Peter Ralph (2012) Is your phylogeny informative? Measuring the power of comparative methods, Evolution 66 (7) 2240-51. doi:10.1111/j.1558-5646.2011.01574.x.
Beta, use with caution!
This is a lightweight implementation of my
pmc package focusing on what I think are the more common use cases (e.g. it will no longer support comparisons of a
geiger model against an
ouch model). Further, it does not cover many of the newer model fitting that have been implemented since
pmc was first released.
The goal of this release is mostly to provide compatibility with current versions of
Install the package:
A trivial example with data simulated from the
phy <- sim.bdtree(n=10)dat <- sim.char(rescale(phy, "lambda", .5), 1)[,1,]out <- pmc(phy, dat, "BM", "lambda", nboot = 50)
Plot the results:
dists <- data.frame(null = out$null, test = out$test)library("ggplot2")library("tidyr")library("dplyr")
## ## Attaching package: 'dplyr' ## The following objects are masked from 'package:stats': ## ## filter, lag ## The following objects are masked from 'package:base': ## ## intersect, setdiff, setequal, union
dists %>%gather(dist, value) %>%ggplot(aes(value, fill = dist)) +geom_density(alpha = 0.5) +geom_vline(xintercept = out$lr)
Carl Boettiger, Graham Coop, Peter Ralph (2012) Is your phylogeny informative? Measuring the power of comparative methods, Evolution 66 (7) 2240-51. http://doi.org/10.1111/j.1558-5646.2011.01574.x
For a complete discription of changes see the Issues page on the package development site on GitHub.