The Problem With Bayesian Model Averaging…

December 3, 2017
By

(This article was originally published at No Hesitations, and syndicated at StatsBlogs.)

The problem is that one of the models considered is traditionally assumed true (explicitly or implicitly) since the prior model probabilities sum to one. Hence all posterior weight gets placed on a single model asymptotically -- just what you don't want when constructing a portfolio of surely-misspecified models. The earliest paper I know that makes and explores this point is one of mine, here. Recent and ongoing research is starting to address it much more thoroughly, for example here and here. (Thanks to Veronika Rockova for sending.)






Please comment on the article here: No Hesitations


Subscribe

Email:

  Subscribe