Classic paper: Glynn & Iglehart (1989) …

The coincidence of a number of different projects has led me to an increasing interest in importance sampling for stochastic processes (in particular, DPs and GPs).  In this context it’s worth mentioning this classical paper by Glynn & Iglehart: http://www.stanford.edu/~glynn/papers/1989/GI89a.pdf .  If you’re familiar with basic (discrete state space) Markov chain theory (i.e., transition matrices; recurrence times; etc.) and basic importance sampling theory (cf. Hesterberg 1994) then this paper gives a great bridge to importance sampling & Radon-Nikodym derivative theory for (discrete state space) stochastic processes.  (For time-conscious readers I’d say that one get the gist of the paper by reading only the first parts of Sections 2, 3, 5, and 6, skipping over the extensions of each example to functions over infinite histories.)

Advertisements
This entry was posted in Statistics. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s