Properties of Nested Sampling
Robert, Christian P.; Chopin, Nicolas (2010), Properties of Nested Sampling, Biometrika, 97, 3, p. 741-755. http://dx.doi.org/10.1093/biomet/asq021
TypeArticle accepté pour publication ou publié
External document linkhttp://hal.archives-ouvertes.fr/hal-00216003/en/
Oxford University Press
MetadataShow full item record
Abstract (EN)Nested sampling is a simulation method for approximating marginal likelihoods proposed by Skilling (2006). We establish that nested sampling has an approximation error that vanishes at the standard Monte Carlo rate N−1/2, where N is a tuning parameter proportional to the computational effort, and that this error is asymptotically Gaussian.We show that the asymptotic variance of the nested sampling approximation typically grows linearly with the dimension of the parameter. We discuss the applicability and efficiency of nested sampling in realistic problems, and we compare it with two current methods for computing marginal likelihood. We propose an extension that makes it possible to avoid resorting to MCMC to obtain the simulated points.
Subjects / KeywordsMarkov chain Monte Carlo simulation; Evidence; importance sampling; Nested sampling; Marginal likelihood; Central limit theorem
Showing items related by title and author.
Some discussions of D. Fearnhead and D. Prangle's Read Paper "Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation" Singh, Sumeetpal S.; Sedki, Mohammed; Jasra, Ajay; Pudlo, Pierre; Robert, Christian P.; Lee, Anthony; Marin, Jean-Michel; Kosmidis, Ioannis; Girolami, Mark; Andrieu, Christophe; Cornebise, Julien; Doucet, Arnaud; Barthelme, Simon; Chopin, Nicolas (2012) Article accepté pour publication ou publié