|
Activity Number:
|
207
|
|
Type:
|
Roundtables
|
|
Date/Time:
|
Monday, August 1, 2016 : 12:30 PM to 1:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #319077
|
|
|
Title:
|
Bayesian Model Selection
|
|
Author(s):
|
Philip Dawid*
|
|
Companies:
|
University of Cambridge
|
|
Keywords:
|
priors ;
objective Bayes
|
|
Abstract:
|
The "compleat Bayesian" approach to model selection is totally straightforward-so long as we have well-specified proper prior distributions. Many folks worry about sensitivity to the choice of priors and would like a more objective approach. However, switching to improper priors is highly problematic. There have been numerous attempts to get around these problems. How well do they succeed?
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2016 program
|
