Abstract #300258

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #300258
Activity Number: 43
Type: Topic Contributed
Date/Time: Sunday, August 3, 2003 : 4:00 PM to 5:50 PM
Sponsor: Section on Bayesian Stat. Sciences
Abstract - #300258
Title: Constructing Hierarchical Priors
Author(s): Li-Jung Liang*+ and Robert E. Weiss
Companies: University of California, Los Angeles and University of California, Los Angeles
Address: 3161 S. Sepulveda Blvd., Los Angeles, CA, 90034-4266,
Keywords: hierarchical model ; Dirichlet mixture process ; MCMC
Abstract:

We discuss development of a model and computational algorithm to be used in constructing hierarchical priors. We assume that we have a number of exchangeable datasets and analyses. Each individual dataset and model takes a long time to run using Markov Chain Monte Carlo. The individual datasets and models have been fit using noninformative priors for some of the model parameters and we have MCMC samples from those posteriors. We wish to efficiently improve the single dataset inferences by incorporating information from the multiple datasets, and to possibly come up with generic informative priors for future studies. We develop a nonparametric Dirichlet process prior for the hyperprior of the individual level parameters. Since we already have MCMC samples from the individual analyses, and we do not wish to rerun the models at the individual level, we use an importance reweighting algorithm for the parameters at the individual level.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003