GRIMS is an R package for performing MCMC simulations, for distributions that are defined using R functions, using Markov sampling methods that are defined by R functions. In particular, it has implementations of some variations on Hamiltonian Monte Carlo (HMC), as mentioned in my review paper on HMC.

This preliminary version, released 2012-06-07, is not yet structured as a proper R package, and has only a few example distributions and example sampling methods. It may also have lots of bugs. There is some discussion of GRIMS at my blog.

You can get the R functions and documentation files in this tar file or this zip file.

If you want to browse the documentation immedately, you can look at the documentation files below:

overview.txtand here is the README file.

mcmc.txt

lpr_fun.txt

update_fun.txt

singlevar.txt

Previous releases (tar files):

2011-08-26

2011-08-10

2011-06-28

2011-06-25

Back to Radford Neal's home page