From Andrew Gelman, some "important methods and concepts related to statistics that are not as well known as they should be."
I have what is essentially a Metropolis-within-Gibbs sampler. One or two of the parameters have unconventional steps in their sampling. (I'm talking about my expansion to Challis Schmidler 2012 which used a library of proposals to improve mixing on a couple of the parameters). I suspect I'm seeing poor mixing in some of the other parameters, so I wondered if I could use Stan for those parameters and keep the library-based sampler as well.
Quick Google search reveals ... I'm not sure what. From this post on the Stan Google group, the following quotes are pertinent in answer to a question about (I thought) using HMC together with another type of sampler for one of the parameters. It seems the questioner has either a hierarchical or discrete model (both bad for Stan) and that in the later quotes it appears I could alternate Stan with RWMetropolis. Read on... This page discusses use of the commands saveRDS() and readRDS() as replacements for save() and load()
|
Categories
All
Archives
December 2016
AboutThis blog is mainly for statistics, R, or Duke-related stuff that is not directly relating to research activity. |