NEW MODELS FOR MARKOV RANDOM-FIELDS

被引：13

作者：

CRESSIE, N ^{[1
]}

LELE, S ^{[1
]}

机构：

[1] JOHNS HOPKINS UNIV,DEPT BIOSTAT,BALTIMORE,MD 21218

来源：

JOURNAL OF APPLIED PROBABILITY | 1992年 / 29卷 / 04期

关键词：

AUTOMODELS; CONDITIONAL DISTRIBUTIONS; EXPONENTIAL FAMILIES; HAMMERSLEY-CLIFFORD THEOREM; NEIGHBORHOODS;

D O I：

10.2307/3214720

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：

The Hammersley-Clifford theorem gives the form that the joint probability density (or mass) function of a Markov random field must take. Its exponent must be a sum of functions of variables, where each function in the summand involves only those variables whose sites form a clique. From a statistical modeling point of view, it is important to establish the converse result, namely, to give the conditional probability specifications that yield a Markov random field. Besag (1974) addressed this question by developing a one-parameter exponential family of conditional probability models. In this article, we develop new models for Markov random fields by establishing sufficient conditions for the conditional probability specifications to yield a Markov random field.

引用

页码：877 / 884

页数：8