|
Activity Number:
|
347
- Computationally Intensive Bayesian Methodology
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #305257
|
|
|
Title:
|
Bayesian Sampling in Constrained Domains
|
|
Author(s):
|
Sharang Chaudhry* and Kaushik Ghosh and Daniel Lautzenheiser
|
|
Companies:
|
University of Nevada Las Vegas and University of Nevada Las Vegas and University of Nevada Las Vegas
|
|
Keywords:
|
MCMC;
Metropolis-Hastings;
sum-to-one;
simplex;
domain constraint
|
|
Abstract:
|
Picking optimal proposal distributions for Bayesian sampling is a well known yet challenging problem. Its difficulty can get exacerbated when working with parameters that have domain constraints. In this work, a transformation called inversion in a sphere is used within the Metropolis-Hastings framework to make the constrained sets more amenable to sampling. The proposed scheme is demonstrated across two examples with comparative analyses and applications.
|
Authors who are presenting talks have a * after their name.
