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.
|Date of creation:||07 Mar 2006|
|Contact details of provider:|| Postal: Pavillon Lucien Brault, 101 rue Saint Jean-Bosco, Gatineau (Québec) J8Y 3G5|
Phone: (819) 595-3900
Fax: (819) 773-1747
Web page: http://www.repad.org/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:pqs:wpaper:062006. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Christian Calmes)
If references are entirely missing, you can add them using this form.