Campillo, Fabien and Cantet, Philippe and Rakotozafy, Rivo and Rossi, Vivien - Méthodes MCMC en interaction pour l'évaluation de ressources naturelles

arima:1887 - Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées, August 11, 2016, Volume 8, Special Issue CARI'06, 2008
Méthodes MCMC en interaction pour l'évaluation de ressources naturelles

Authors: Campillo, Fabien and Cantet, Philippe and Rakotozafy, Rivo and Rossi, Vivien

Markov chain Monte Carlo (MCMC) methods together with hidden Markov models are extensively used in the Bayesian inference for many scientific fields like environment and ecology. Through simulated examples we show that the speed of convergence of these methods can be very low. In order to improve the convergence properties, we propose a method to make parallel chains interact. We apply this method to a biomass evolution model for fisheries.


Source : oai:HAL:inria-00506386v1
Volume: Volume 8, Special Issue CARI'06, 2008
Published on: August 11, 2016
Submitted on: August 11, 2016
Keywords: Bayesian inference,Markov chain Monte Carlo,Inférence bayésienne,Monte Carlo par chaîne de Markov,[MATH.MATH-PR] Mathematics [math]/Probability [math.PR]


Share

Consultation statistics

This page has been seen 39 times.
This article's PDF has been downloaded 46 times.