Thumbnail

Explaining the Perfect Sampler

Casella, George; Lavine, Michael; Robert, Christian P. (2001), Explaining the Perfect Sampler, The American Statistician, 55, 4, p. 299-305. http://dx.doi.org/10.1198/000313001753272240

View/Open
Type
Article accepté pour publication ou publié
Date
2001
Journal name
The American Statistician
Volume
55
Number
4
Publisher
American Statistical Association
Pages
299-305
Publication identifier
Metadata
Show full item record
Author(s)
Casella, George
Lavine, Michael
Robert, Christian P.
Abstract (EN)
In 1996, Propp and Wilson introduced coupling from the past (CFTP), an algorithm for generating a sample from the exact stationary distribution of a Markov chain. In 1998, Fill proposed another so–called perfect sampling algorithm. These algorithms have enormous potential in Markov Chain Monte Carlo (MCMC) problems because they eliminate the need to monitor convergence and mixing of the chain. This article provides a brief introduction to the algorithms, with an emphasis on understanding rather than technical detail.
Subjects / Keywords
Coupling from the past; Fill's algorithm; Markov Chain Monte Carlo; Stochastic processes
JEL
C15 - Statistical Simulation Methods: General