JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 250
Type: Contributed
Date/Time: Monday, July 30, 2012 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract - #304198
Title: Computing Marginal Likelihoods Using Generalized Direct Sampling
Author(s): Michael Braun*+
Companies: MIT Sloan School of Management
Address: One Amherst St, Cambridge, MA, 02142, United States
Keywords: model comparison ; Bayes factors ; parallel computation ; simulation ; Bayesian estimation ; hierarchical models

Generalized Direct Sampling (GDS) is a method for estimating parameters of high-dimensional non-conjugate hierarchical models. Samples from the posterior distribution are independent, so they can be collected in parallel, with no concern for issues like MCMC chain convergence or autocorrelation. In this talk, I will explain how GDS allows the researcher to estimate the marginal likelihood of the data. The method is stable, fast, generally applicable to a broad class of hierarchical models.

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 2012 program

2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.