[Statlist] Reminder *Research seminar in statistics* Université de Genève / Faculté SES

[Sylvie Huber]

RESEARCH SEMINAR IN STATISTICS



Organisers :                                                                                   .

E. Cantoni - E. Ronchetti - S. Sperlich - M-P. Victoria-Feser



Friday November 15th, 2013

at 11h15

Room M 5220, Uni Mail (40, bd du Pont-d'Arve)



Arnaud Doucet

Oxford Université



Efficient implementation of MCMC when using an unbiased likelihood estimator

Abstract: When an unbiased estimator of the likelihood is used within an Markov chain Monte Carlo (MCMC) scheme as in particle MCMC, it is necessary to tradeoff the number of samples used against the computing time. Many samples for the estimator will result in a MCMC scheme which has similar properties to the case where the likelihood is exactly known but will be expensive. Few samples for the construction of the estimator will result in faster estimation but at the expense of slower mixing of the Markov chain. We explore the relationship between the number of samples and the efficiency of the resulting MCMC estimates. Under specific assumptions about the likelihood estimator, we are able to provide guidelines on the number of samples to select for a general Metropolis-Hastings proposal. We provide theory which validates the use of these assumptions for a large class of models. On a number of realistic examples, we find that the assumptions on the likelihood estimator are accurate.



http://www.stat-center.unige.ch/ResSem.html

Sylvie Huber
Université de Genève
Département des sciences économiques
Secrétaire

Bureau 5263, 5ème étage
UNI MAIL, Bd du Pont d'Arve 40
Suisse - 1211 Genève 4
Tél. : + 41 22 379 82 63
Fax : + 41 22 379 82 93
E-mail : Sylvie.Huber at unige.ch<mailto:Sylvie.Huber at unige.ch>


	[[alternative HTML version deleted]]