Adaptive approximate Bayesian computation

Robert, Christian P.; Marin, Jean-Michel; Cornuet, Jean-Marie; Beaumont, Mark A.

Robert, Christian P.; Marin, Jean-Michel; Cornuet, Jean-Marie; Beaumont, Mark A. (2009), Adaptive approximate Bayesian computation, Biometrika, 96, 4, p. 983-990. http://dx.doi.org/10.1093/biomet/asp052

Type

Article accepté pour publication ou publié

Lien vers un document non conservé dans cette base

http://hal.archives-ouvertes.fr/hal-00280461/en/

Date

2009

Nom de la revue

Biometrika

Volume

Numéro

Éditeur

Oxford University Press

Pages

983-990

Résumé (EN)

Sequential techniques can enhance the efficiency of the approximate Bayesian computation algorithm, as in Sisson et al.’s (2007) partial rejection control version. While this method is based upon the theoretical works of Del Moral et al. (2006), the application to approximate Bayesian computation results in a bias in the approximation to the posterior. An alternative version based on genuine importance sampling arguments bypasses this difficulty, in connection with the population Monte Carlo method of Cappé et al. (2004), and it includes an automatic scaling of the forward kernel. When applied to a population genetics example, it compares favourably with two other versions of the approximate algorithm.

Mots-clés

Importance sampling; Markov chain Monte Carlo; Partial rejection control; Sequential Monte Carlo