An iterative Monte Carlo method for nonconjugate Bayesian analysis

Bradley P. Carlin; Alan E. Gelfand

doi:10.1007/BF01889986

An iterative Monte Carlo method for nonconjugate Bayesian analysis

Bradley P. Carlin, Alan E. Gelfand

Research output: Contribution to journal › Article › peer-review

31 Scopus citations

Abstract

The Gibbs sampler has been proposed as a general method for Bayesian calculation in Gelfand and Smith (1990). However, the predominance of experience to date resides in applications assuming conjugacy where implementation is reasonably straightforward. This paper describes a tailored approximate rejection method approach for implementation of the Gibbs sampler when nonconjugate structure is present. Several challenging applications are presented for illustration.

Original language	English (US)
Pages (from-to)	119-128
Number of pages	10
Journal	Statistics and Computing
Volume	1
Issue number	2
DOIs	https://doi.org/10.1007/BF01889986
State	Published - Dec 1991
Externally published	Yes

Keywords

Bayesian inference
Gibbs sampler
hierarchical models
logistic regression
nonlinear models
rejection method

Access

10.1007/BF01889986

OpenUrl availability

Full text

Cite this

@article{86667fa7fea549f8911a6d5052152a69,

title = "An iterative Monte Carlo method for nonconjugate Bayesian analysis",

abstract = "The Gibbs sampler has been proposed as a general method for Bayesian calculation in Gelfand and Smith (1990). However, the predominance of experience to date resides in applications assuming conjugacy where implementation is reasonably straightforward. This paper describes a tailored approximate rejection method approach for implementation of the Gibbs sampler when nonconjugate structure is present. Several challenging applications are presented for illustration.",

keywords = "Bayesian inference, Gibbs sampler, hierarchical models, logistic regression, nonlinear models, rejection method",

author = "Carlin, {Bradley P.} and Gelfand, {Alan E.}",

year = "1991",

month = dec,

doi = "10.1007/BF01889986",

language = "English (US)",

volume = "1",

pages = "119--128",

journal = "Statistics and Computing",

issn = "0960-3174",

publisher = "Springer Netherlands",

number = "2",

}

TY - JOUR

T1 - An iterative Monte Carlo method for nonconjugate Bayesian analysis

AU - Carlin, Bradley P.

AU - Gelfand, Alan E.

PY - 1991/12

Y1 - 1991/12

N2 - The Gibbs sampler has been proposed as a general method for Bayesian calculation in Gelfand and Smith (1990). However, the predominance of experience to date resides in applications assuming conjugacy where implementation is reasonably straightforward. This paper describes a tailored approximate rejection method approach for implementation of the Gibbs sampler when nonconjugate structure is present. Several challenging applications are presented for illustration.

AB - The Gibbs sampler has been proposed as a general method for Bayesian calculation in Gelfand and Smith (1990). However, the predominance of experience to date resides in applications assuming conjugacy where implementation is reasonably straightforward. This paper describes a tailored approximate rejection method approach for implementation of the Gibbs sampler when nonconjugate structure is present. Several challenging applications are presented for illustration.

KW - Bayesian inference

KW - Gibbs sampler

KW - hierarchical models

KW - logistic regression

KW - nonlinear models

KW - rejection method

UR - http://www.scopus.com/inward/record.url?scp=0042759311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042759311&partnerID=8YFLogxK

U2 - 10.1007/BF01889986

DO - 10.1007/BF01889986

M3 - Article

AN - SCOPUS:0042759311

SN - 0960-3174

VL - 1

SP - 119

EP - 128

JO - Statistics and Computing

JF - Statistics and Computing

IS - 2

ER -

An iterative Monte Carlo method for nonconjugate Bayesian analysis

Abstract

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this