Bayesian graphical modelling: a case-study in monitoring health outcomes

被引：88

作者：

Spiegelhalter, DJ ^{[1
]}

机构：

[1] Inst Publ Hlth, Medical Research Council, Biostat Unit, Cambridge CB2 2SR, England

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS | 1998年 / 47卷

关键词：

cancer incidence; cervical screening; Gibbs sampling; hierarchical models; Markov chain Monte Carlo methods;

D O I：

10.1111/1467-9876.00101

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：

Bayesian graphical modelling represents the synthesis of several recent developments in applied complex modelling. After describing a moderately challenging real example, we show how graphical models and Markov chain Monte Carte methods naturally provide a direct path between model specification and the computational means of making inferences on that model. These ideas are illustrated with a range of modelling issues related to our example. An appendix discusses the BUGS software.

引用

页码：115 / 133

页数：19

共 54 条

[1]

ANDERSEN SK, 1989, P 11 INT JOINT C ART, P1080

[2]

[Anonymous], 1995, CODA CONVERGENCE DIA

[3]

[Anonymous], 1993, Modelling covariances and latent variables using EQS

[4]

Arjas E, 1996, STAT MED, V15, P1757, DOI 10.1002/(SICI)1097-0258(19960830)15:16<1757::AID-SIM336>3.0.CO

[5]

2-J

[6]

ARJAS E, 1997, STAT MED, V16, P741

[7]

Bernardinelli L, 1997, STAT MED, V16, P741, DOI 10.1002/(SICI)1097-0258(19970415)16:7<741::AID-SIM501>3.0.CO

[8]

2-1

[9] Bayesian analysis of realistically complex models [J].

Best, NG ;

Spiegelhalter, DJ ;

Thomas, A ;

Brayne, CEG .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY, 1996, 159 :323-342

[10] Statistics in epidemiology: The case-control study [J].

Breslow, NE .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1996, 91 (433) :14-28

← 1 2 3 4 5 6 →