|
Activity Number:
|
419
- Bayesian Computation and Spatial Modeling
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #329507
|
Presentation
|
|
Title:
|
A New Diagnostic for MCMC Output Analysis
|
|
Author(s):
|
Nathan Lane Robertson* and James Flegal
|
|
Companies:
|
University of California, Riverside and University of California, Riverside
|
|
Keywords:
|
MCMC;
Markov Chain Monte Carlo;
Sequential Stopping Rules
|
|
Abstract:
|
In MCMC sampling one samples from an approximate target distribution to generate strongly consistent estimates of a target parameter. One question that garners attention in any sampling procedure is how many samples should be drawn? Sequential stopping rules provide asymptotically valid stopping times based on confidence intervals in when there exist a MCMC central limit theorem. Recent advancements have provided multivariate sequential stopping rules for expectations of multivariate target distributions based on confidence regions. This work extends these results to multivariate sequential stopping rules for more general parameter estimation.
|
Authors who are presenting talks have a * after their name.
