Affordable Access

Publisher Website

Perfect sampling for Bayesian variable selection in a linear regression model

Authors
Journal
Journal of Statistical Planning and Inference
0378-3758
Publisher
Elsevier
Publication Date
Volume
126
Issue
1
Identifiers
DOI: 10.1016/j.jspi.2003.09.009
Keywords
  • Invariant Measures
  • Backwards Coupling
  • Coupling From The Past
  • Exact Sampling
  • Perfect Sampling
  • Slice Coupling
  • Shift Coupling
  • Bayesian Variable Selection
Disciplines
  • Computer Science

Abstract

Abstract We describe the use of perfect sampling algorithms for Bayesian variable selection in a linear regression model. Starting with a basic case solved by Huang and Djurić (EURASIP J. Appl. Si. Pr. 1 (2002) 38), where the model coefficients and noise variance are assumed to be known, we generalize the model step by step to allow for other sources of randomness. We specify perfect simulation algorithms that solve these cases by incorporating various techniques including Gibbs sampling, the perfect independent Metropolis–Hastings (IMH) algorithm, and recently developed “slice coupling” algorithms. Applications to simulated data sets suggest that our algorithms perform well in identifying relevant predictor variables.

There are no comments yet on this publication. Be the first to share your thoughts.