Sequential MCMC for Bayesian model selection
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 130-134
- https://doi.org/10.1109/host.1999.778709
Abstract
In this paper, we address the problem of sequential Bayesian model selection. This problem does not usually admit any closed-form analytical solution. We propose here an original sequential simulation-based method to solve the associated Bayesian computational problems. This method combines sequential importance sampling, a resampling procedure and reversible jump MCMC (Markov chain Monte Carlo) moves. We describe a generic algorithm and then apply it to the problem of sequential Bayesian model order estimation of autoregressive (AR) time series observed in additive noise.Keywords
This publication has 13 references indexed in Scilit:
- Sequential importance sampling for nonparametric Bayes models: The next generationThe Canadian Journal of Statistics / La Revue Canadienne de Statistique, 1999
- Filtering via Simulation: Auxiliary Particle FiltersJournal of the American Statistical Association, 1999
- Asymptotic MAP criteria for model selectionIEEE Transactions on Signal Processing, 1998
- Sequential Monte Carlo Methods for Dynamic SystemsJournal of the American Statistical Association, 1998
- Dynamic Conditional Independence Models and Markov Chain Monte Carlo MethodsJournal of the American Statistical Association, 1997
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determinationBiometrika, 1995
- Markov Chains for Exploring Posterior DistributionsThe Annals of Statistics, 1994
- Novel approach to nonlinear/non-Gaussian Bayesian state estimationIEE Proceedings F Radar and Signal Processing, 1993
- Bayesian Inference in Econometric Models Using Monte Carlo IntegrationEconometrica, 1989
- Stochastic SimulationWiley Series in Probability and Statistics, 1987