U. Schneider and J.N. Corcoran
Journal of Statistical Planning and Inference (JSPI) 2004, 126 (1), 153-171.
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 Djuric (2002), 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, specifying 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.
Link to paper (JSPI)