No Cover Image

Journal article 202 views

A Non-monotone CFTP perfect simulation method / Yuzhi Cai

Statistica Sinica, Volume: 15, Pages: 927 - 943

Swansea University Author: Cai, Yuzhi

Abstract

In this paper, we present a non-monotone coupling from the past (CFTP)method for obtaining perfect samples from the equilibrium distribution of a Markovchain. This method requires no monotone structure that is dicult to dene inpractice. We also apply the non-monotone CFTP method to general non-monot...

Full description

Published in: Statistica Sinica
Published: 2005
URI: https://cronfa.swan.ac.uk/Record/cronfa15294
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: In this paper, we present a non-monotone coupling from the past (CFTP)method for obtaining perfect samples from the equilibrium distribution of a Markovchain. This method requires no monotone structure that is dicult to dene inpractice. We also apply the non-monotone CFTP method to general non-monotonebirth-death processes and area-interaction point processes.
Keywords: Area-interaction point processes, birth-death processes, CFTP, MCMC, monotone, non-monotone, perfect simulation.
College: School of Management
Start Page: 927
End Page: 943