|
Activity Number:
|
202
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #304280 |
|
Title:
|
A Short Note on Bayesian Analysis of Dynamic Probit Models
|
|
Author(s):
|
Minje Sung*+ and Refik Soyer
|
|
Companies:
|
Ajou University and The George Washington University
|
|
Address:
|
San 5, Woncheon-dong, Suwon, International, 443-749, Korea
|
|
Keywords:
|
Markov models ; Bayesian inference ; longitudinal data ; dynamic linear models ; model selection
|
|
Abstract:
|
In this talk we consider a dynamic probit model where the coefficients follow a first-order Markov process. We present an exact Gibbs sampler for Bayesian analysis of the model using the data augmentation approach of Albert and Chib (1993) and the forward filtering backward sampling algorithm of Fruhwirth-Schnatter (1994) for dynamic linear models. We discuss how our approach can be used for probit based Markov regression models.
|
