Activity Number:
|
303
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 14, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Computing*
|
Abstract - #300611 |
Title:
|
Honest Exploration of Intractable Probability Distributions Via Markov Chain Monte Carlo
|
Author(s):
|
James Hobert*+ and Galin Jones
|
Affiliation(s):
|
University of Florida and University of Minnesota
|
Address:
|
203 Griffin-Floyd Hall, Gainesville, Florida, 32611, USA
|
Keywords:
|
Minorization condition ; Central limit theorem ; Convergence rate ; Drift condition ; Regeneration
|
Abstract:
|
Two important questions that must be answered whenever a Markov chain Monte Carlo algorithm is used are (Q1) What is an appropriate burn-in? and (Q2) How long should the sampling continue after burn-in? One method of developing rigorous answers to these questions involves establishing drift and minorization conditions, which together imply that the underlying Markov chain is geometrically ergodic. In this talk, I will explain exactly what drift and minorization are, as well as how and why these conditions can be used to form rigorous answers to (Q1) and (Q2).
|