Particle Learning for Sequential Bayesian Computation

Hedibert F. Lopes; Michael S. Johannes; Carlos M. Carvalho; Nicholas G. Polson; Michael Pitt

doi:10.1093/acprof:oso/9780199694587.003.0011

Particle Learning for Sequential Bayesian Computation

Hedibert F. Lopes, Michael S. Johannes, Carlos M. Carvalho, Nicholas G. Polson, Michael Pitt

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Particle learning provides a simulation-based approach to sequential Bayesian computation. To sample from a posterior distribution of interest we use an essential state vector together with a predictive distribution and propagation rule to build a resampling-sampling framework. Predictive inference and sequential Bayes factors are a direct by-product. Our approach provides a simple yet powerful framework for the construction of sequential posterior sampling strategies for a variety of commonly used models.

Original language	English (US)
Title of host publication	Bayesian Statistics 9
Publisher	Oxford University Press
Volume	9780199694587
ISBN (Electronic)	9780191731921
ISBN (Print)	9780199694587
DOIs	https://doi.org/10.1093/acprof:oso/9780199694587.003.0011
State	Published - Jan 19 2012
Externally published	Yes

Keywords

Bayesian
Conditional dynamic linear models
Dirichlet
Dynamic factor models
Essential state vector
Mixture models
Nonparametric
Particle learning
Sequential inference

ASJC Scopus subject areas

General Mathematics

Access to Document

10.1093/acprof:oso/9780199694587.003.0011

Cite this

@inbook{9c5d6a6bb1f644cc9399c6a8cc6307d9,

title = "Particle Learning for Sequential Bayesian Computation",

abstract = "Particle learning provides a simulation-based approach to sequential Bayesian computation. To sample from a posterior distribution of interest we use an essential state vector together with a predictive distribution and propagation rule to build a resampling-sampling framework. Predictive inference and sequential Bayes factors are a direct by-product. Our approach provides a simple yet powerful framework for the construction of sequential posterior sampling strategies for a variety of commonly used models.",

keywords = "Bayesian, Conditional dynamic linear models, Dirichlet, Dynamic factor models, Essential state vector, Mixture models, Nonparametric, Particle learning, Sequential inference",

author = "Lopes, {Hedibert F.} and Johannes, {Michael S.} and Carvalho, {Carlos M.} and Polson, {Nicholas G.} and Michael Pitt",

year = "2012",

month = jan,

day = "19",

doi = "10.1093/acprof:oso/9780199694587.003.0011",

language = "English (US)",

isbn = "9780199694587",

volume = "9780199694587",

booktitle = "Bayesian Statistics 9",

publisher = "Oxford University Press",

}

TY - CHAP

T1 - Particle Learning for Sequential Bayesian Computation

AU - Lopes, Hedibert F.

AU - Johannes, Michael S.

AU - Carvalho, Carlos M.

AU - Polson, Nicholas G.

AU - Pitt, Michael

PY - 2012/1/19

Y1 - 2012/1/19

N2 - Particle learning provides a simulation-based approach to sequential Bayesian computation. To sample from a posterior distribution of interest we use an essential state vector together with a predictive distribution and propagation rule to build a resampling-sampling framework. Predictive inference and sequential Bayes factors are a direct by-product. Our approach provides a simple yet powerful framework for the construction of sequential posterior sampling strategies for a variety of commonly used models.

AB - Particle learning provides a simulation-based approach to sequential Bayesian computation. To sample from a posterior distribution of interest we use an essential state vector together with a predictive distribution and propagation rule to build a resampling-sampling framework. Predictive inference and sequential Bayes factors are a direct by-product. Our approach provides a simple yet powerful framework for the construction of sequential posterior sampling strategies for a variety of commonly used models.

KW - Bayesian

KW - Conditional dynamic linear models

KW - Dirichlet

KW - Dynamic factor models

KW - Essential state vector

KW - Mixture models

KW - Nonparametric

KW - Particle learning

KW - Sequential inference

UR - http://www.scopus.com/inward/record.url?scp=84933474403&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933474403&partnerID=8YFLogxK

U2 - 10.1093/acprof:oso/9780199694587.003.0011

DO - 10.1093/acprof:oso/9780199694587.003.0011

M3 - Chapter

AN - SCOPUS:84933474403

SN - 9780199694587

VL - 9780199694587

BT - Bayesian Statistics 9

PB - Oxford University Press

ER -

Particle Learning for Sequential Bayesian Computation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this