Perfect Simulation for a Class of Positive Recurrent Markov Chains

Stephen Connor; W.S. Kendall

doi:10.1214/105051607000000032

Perfect Simulation for a Class of Positive Recurrent Markov Chains

Stephen Connor, W.S. Kendall

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

This paper generalises the work of Kendall (2004), which showed that perfect simulation, in the form of dominated coupling from the past, is always possible (though not necessarily practical) for geometrically ergodic Markov chains. Here we consider the more general situation of positive recurrent chains, and explore when it is possible to produce such a simulation algorithm for these chains. We introduce a class of chains which we name tame, for which we show that perfect simulation is possible.

Original language	English
Pages (from-to)	781-808
Number of pages	28
Journal	The Annals of Applied Probability
Volume	17 (3)
DOIs	https://doi.org/10.1214/105051607000000032
Publication status	Published - 2007

Keywords

Statistics

Access to Document

10.1214/105051607000000032

http://arxiv.org/abs/math.PR/0601174

Cite this

@article{113e18cfbfb047f79e4cedba49d2b090,

title = "Perfect Simulation for a Class of Positive Recurrent Markov Chains",

abstract = "This paper generalises the work of Kendall (2004), which showed that perfect simulation, in the form of dominated coupling from the past, is always possible (though not necessarily practical) for geometrically ergodic Markov chains. Here we consider the more general situation of positive recurrent chains, and explore when it is possible to produce such a simulation algorithm for these chains. We introduce a class of chains which we name tame, for which we show that perfect simulation is possible.",

keywords = "Statistics",

author = "Stephen Connor and W.S. Kendall",

year = "2007",

doi = "10.1214/105051607000000032",

language = "English",

volume = "17 (3)",

pages = "781--808",

journal = "The Annals of Applied Probability",

publisher = "Institute of Mathematical Statistics",

}

TY - JOUR

T1 - Perfect Simulation for a Class of Positive Recurrent Markov Chains

AU - Connor, Stephen

AU - Kendall, W.S.

PY - 2007

Y1 - 2007

N2 - This paper generalises the work of Kendall (2004), which showed that perfect simulation, in the form of dominated coupling from the past, is always possible (though not necessarily practical) for geometrically ergodic Markov chains. Here we consider the more general situation of positive recurrent chains, and explore when it is possible to produce such a simulation algorithm for these chains. We introduce a class of chains which we name tame, for which we show that perfect simulation is possible.

AB - This paper generalises the work of Kendall (2004), which showed that perfect simulation, in the form of dominated coupling from the past, is always possible (though not necessarily practical) for geometrically ergodic Markov chains. Here we consider the more general situation of positive recurrent chains, and explore when it is possible to produce such a simulation algorithm for these chains. We introduce a class of chains which we name tame, for which we show that perfect simulation is possible.

KW - Statistics

U2 - 10.1214/105051607000000032

DO - 10.1214/105051607000000032

M3 - Article

VL - 17 (3)

SP - 781

EP - 808

JO - The Annals of Applied Probability

JF - The Annals of Applied Probability

ER -