A multi-move sampler for estimating non-Gaussian time series models: Comments on Shephard & Pitt (1997)

被引：79

作者：

Watanabe, T

Omori, Y

机构：

[1] Tokyo Metropolitan Univ, Fac Econ, Tokyo 1920397, Japan

[2] Univ Tokyo, Fac Econ, Bunkyo Ku, Tokyo 1130033, Japan

来源：

关键词：

Markov chain Monte Carlo; multi-move sampler; simulation smoother; state variable;

D O I：

10.1093/biomet/91.1.246

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

This note points out a problem in the multi-move sampler as proposed by Shephard & Pitt (1997) and provides an alternative correct formulation.

引用

页码：246 / 248

页数：3

共 5 条

[1]

DEJONG P, 1995, BIOMETRIKA, V82, P339

[2]

Pitt MK, 1999, BAYESIAN STATISTICS 6, P547

[3] Likelihood analysis of non-Gaussian measurement time series [J].

Shephard, N ;

Pitt, MK .

[4]

TIERNEY L, 1994, ANN STAT, V22, P1701, DOI 10.1214/aos/1176325750

Watanabe, T .