EXACT ESTIMATION FOR MARKOV CHAIN EQUILIBRIUM EXPECTATIONS

被引:69
|
作者
Glynn, Peter W. [1 ]
Rhee, Chang-Han [2 ]
机构
[1] Stanford Univ, Management Sci & Engn, Stanford, CA 94305 USA
[2] Georgia Inst Technol, Biomed Engn, Atlanta, GA 30332 USA
基金
美国国家科学基金会;
关键词
Unbiased estimation; Markov chain equilibrium expectation; Markov chain stationary expectation; exact estimation; exact sampling; exact simulation; perfect sampling; perfect simulation; SIMULATION;
D O I
10.1017/S0021900200021392
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We introduce a new class of Monte Carlo methods, which we call exact estimation algorithms. Such algorithms provide unbiased estimators for equilibrium expectations associated with real-valued functionals defined on a Markov chain. We provide easily implemented algorithms for the class of positive Harris recurrent Markov chains, and for chains that are contracting on average. We further argue that exact estimation in the Markov chain setting provides a significant theoretical relaxation relative to exact simulation methods.
引用
收藏
页码:377 / 389
页数:13
相关论文
共 50 条