Resampling from the past to improve on MCMC algorithms

We introduce the idea that resampling from past observations in a Markov Chain Monte Carlo sampler can fasten convergence. We prove that proper resampling from the past does not disturb the limit distribution of the algorithm. We illustrate the method with two examples. The first on a Bayesian analysis of stochastic volatility models and the other on Bayesian phylogeny reconstruction.

MoreLess

Year of publication:	2006-03-07
Authors:	Atchade, Yves
Institutions:	Départment des sciences administratives, Université du Québec en Outaouais (UQO)
Subject:	Monte Carlo methods \| Resampling \| Stochastic volatility models \| Bayesian phylogeny reconstruction

freely available

Full text |

More access options

Check Google Scholar

In German libraries (KVK)

I need help

More details

Extent:	application/pdf
Series:	RePAd Working Paper Series.
Type of publication:	Book / Working Paper
Language:	English
Notes:	Number LRSP-WP2 28 pages
Classification:	C10 - Econometric and Statistical Methods: General. General ; C40 - Econometric and Statistical Methods: Special Topics. General
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005710030