Generate an overparameterized starting point for the MCMC

Description

This function takes a prior function and generates a starting point that can be entered for startpar in the function bayou.mcmc

Usage

1

Arguments

prior

A prior function

tree

A phylogenetic tree of class 'phylo'

dat

A named data vector

Details

This function creates an "overparameterized" starting point for running the mcmc. It gives n-1 tips a unique optimum close to the actual data value. This is useful if you expect steep likelihood peaks that may be hard to find, as these often will be easier to access from this overparameterized model. Generally, the overparameterization will have a very high likelihood and a very low prior.


Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.