Abstract Details
Activity Number:
|
245
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 4, 2014 : 2:00 PM to 2:45 PM
|
Sponsor:
|
Section for Statistical Programmers and Analysts
|
Abstract #314020
|
|
Title:
|
A Quantile-Based Convergence Diagnostic for MCMC
|
Author(s):
|
Michael Lerch*+
|
Companies:
|
Montana State University
|
Keywords:
|
Bayesian Statistics ;
MCMC ;
convergence diagnostic
|
Abstract:
|
A critical part to fitting statistical models with MCMC techniques is to assess the convergence of the Markov chains. In many cases, the motivation to use MCMC is to produce posterior quantiles or intervals. We believe that assessing convergence of MCMC should be motivated by the type of value that will be reported. A different requirement may be imposed if the desired result is a mean, a quantile, or a mode. We present a strategy to assess MCMC convergence of posterior quantile estimates based on resampling of Markov chains to estimate the variability of the quantile estimates. We also show examples of use and comparison to other convergence diagnostics.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.