Optimal scaling for various Metropolis-Hastings algorithms

被引：711

作者：

Roberts, GO ^{[1
]}

Rosenthal, JS

机构：

[1] Univ Lancaster, Fylde Coll, Dept Math & Stat, Lancaster LA1 4YF, England

[2] Univ Toronto, Dept Stat, Toronto, ON M5S 3G3, Canada

来源：

STATISTICAL SCIENCE | 2001年 / 16卷 / 04期

关键词：

adaptive triangulations; AIC; density estimation; extended linear models; finite elements; free knot splines; GCV; linear splines; multivariate splines; regression;

D O I：

10.1214/ss/1015346320

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 review and extend results related to optimal scaling of Metropolis-Hastings algorithms. We present various theoretical results for the high-dimensional limit. We also present simulation studies which confirm the theoretical results in finite-dimensional contexts.

引用

页码：351 / 367

页数：17

共 14 条

[1]

Besag, 1994, J R STAT SOC B, V56, P591, DOI DOI 10.1111/J.2517-6161.1994.TB02000.X

[2] From metropolis to diffusions: Gibbs states and optimal scaling [J].

Breyer, LA ;

Roberts, GO .

STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2000, 90 (02) :181-206

[3]

Gelman A., 1996, BAYESIAN STAT, P599

[4]

JARNER SF, 2001, CONVERGENCE HEAVY TA

[5]

Kennedy A. D., 1991, Nuclear Physics B, Proceedings Supplements, V20, P118, DOI 10.1016/0920-5632(91)90893-J

[6] WEAK CONVERGENCE AND OPTIMAL SCALING OF RANDOM WALK METROPOLIS ALGORITHMS [J].

Roberts, G. O. ;

Gelman, A. ;

Gilks, W. R. .

ANNALS OF APPLIED PROBABILITY, 1997, 7 (01) :110-120

[7]

ROBERTS G. O., 1996, Bernoulli, V2, P341

[8]

Roberts GarethO., 1998, STOCHASTICS STOCHAST, V62, P275, DOI [10.1080/17442509808834136, DOI 10.1080/17442509808834136]

[9] Optimal scaling of discrete approximations to Langevin diffusions [J].

Roberts, GO ;

Rosenthal, JS .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1998, 60 :255-268

[10]

ROBERTS GO, 2001, UNPUB OPTIMAL SCALIN

← 1 2 →