BAYESIAN-ESTIMATION OF HIDDEN MARKOV-CHAINS - A STOCHASTIC IMPLEMENTATION

被引：104

作者：

ROBERT, CP

CELEUX, G

DIEBOLT, J

机构：

[1] UNIV PARIS 06,LSTA,F-75230 PARIS 05,FRANCE

[2] INRIA,ROCQUENCOURT,FRANCE

来源：

STATISTICS & PROBABILITY LETTERS | 1993年 / 16卷 / 01期

关键词：

GIBBS SAMPLING; FORWARD BACKWARD RECURSION FORMULA; ERGODICITY; STOCHASTIC RESTORATION; GEOMETRIC CONVERGENCE;

D O I：

10.1016/0167-7152(93)90127-5

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：

Hidden Markov models lead to intricate computational problems when considered directly. In this paper, we propose an approximation method based on Gibbs sampling which allows an effective derivation of Bayes estimators for these models.

引用

页码：77 / 83

页数：7

共 27 条

[1]

BESAG J, 1993, J ROY STATIST SOC B, V55

[2]

Billingsley P, 1968, CONVERGENCE PROBABIL

[3]

Biscarat J. C., 1992, Stochastic versions of the EM algorithm (No. TR-227)

[4]

CASELLA G, 1992, IN PRESS AM STATIST

[5]

CHAN KS, 1991, 294 U CHIC DEP STAT

[6]

CHURCHILL GA, 1989, B MATH BIOL, V51, P79

[7] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[8] MODELING AND SEGMENTATION OF NOISY AND TEXTURED IMAGES USING GIBBS RANDOM-FIELDS [J].

DERIN, H ;

ELLIOTT, H .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (01) :39-55

[9] BAUM FORWARD - BACKWARD ALGORITHM REVISITED [J].

DEVIJVER, PA .

PATTERN RECOGNITION LETTERS, 1985, 3 (06) :369-373

[10]

DIEBOLT J, 1992, IN PRESS J ROY STATI

← 1 2 3 →