Decoupling shrinkage and selection in bayesian linear models: A posterior summary perspective

P. Richard Hahn; Carlos M. Carvalho

doi:10.1080/01621459.2014.993077

Decoupling shrinkage and selection in bayesian linear models: A posterior summary perspective

P. Richard Hahn, Carlos M. Carvalho

Research output: Contribution to journal › Review article › peer-review

87 Scopus citations

Abstract

Selecting a subset of variables for linear models remains an active area of research. This article reviews many of the recent contributions to the Bayesian model selection and shrinkage prior literature. A posterior variable selection summary is proposed, which distills a full posterior distribution over regression coefficients into a sequence of sparse linear predictors.

Original language	English (US)
Pages (from-to)	435-448
Number of pages	14
Journal	Journal of the American Statistical Association
Volume	110
Issue number	509
DOIs	https://doi.org/10.1080/01621459.2014.993077
State	Published - Jan 2 2015
Externally published	Yes

Keywords

Decision theory
Linear regression
Loss function
Model selection
Parsimony
Shrinkage prior
Sparsity
Variable selection

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1080/01621459.2014.993077

Cite this

@article{238eff194b9d45da93093b613da3c586,

title = "Decoupling shrinkage and selection in bayesian linear models: A posterior summary perspective",

abstract = "Selecting a subset of variables for linear models remains an active area of research. This article reviews many of the recent contributions to the Bayesian model selection and shrinkage prior literature. A posterior variable selection summary is proposed, which distills a full posterior distribution over regression coefficients into a sequence of sparse linear predictors.",

keywords = "Decision theory, Linear regression, Loss function, Model selection, Parsimony, Shrinkage prior, Sparsity, Variable selection",

author = "Hahn, {P. Richard} and Carvalho, {Carlos M.}",

note = "Publisher Copyright: {\textcopyright} 2015, American Statistical Association.",

year = "2015",

month = jan,

day = "2",

doi = "10.1080/01621459.2014.993077",

language = "English (US)",

volume = "110",

pages = "435--448",

journal = "Journal of the American Statistical Association",

issn = "0162-1459",

publisher = "Taylor and Francis Ltd.",

number = "509",

}

TY - JOUR

T1 - Decoupling shrinkage and selection in bayesian linear models

T2 - A posterior summary perspective

AU - Hahn, P. Richard

AU - Carvalho, Carlos M.

PY - 2015/1/2

Y1 - 2015/1/2

N2 - Selecting a subset of variables for linear models remains an active area of research. This article reviews many of the recent contributions to the Bayesian model selection and shrinkage prior literature. A posterior variable selection summary is proposed, which distills a full posterior distribution over regression coefficients into a sequence of sparse linear predictors.

AB - Selecting a subset of variables for linear models remains an active area of research. This article reviews many of the recent contributions to the Bayesian model selection and shrinkage prior literature. A posterior variable selection summary is proposed, which distills a full posterior distribution over regression coefficients into a sequence of sparse linear predictors.

KW - Decision theory

KW - Linear regression

KW - Loss function

KW - Model selection

KW - Parsimony

KW - Shrinkage prior

KW - Sparsity

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=84928252357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928252357&partnerID=8YFLogxK

U2 - 10.1080/01621459.2014.993077

DO - 10.1080/01621459.2014.993077

M3 - Review article

AN - SCOPUS:84928252357

SN - 0162-1459

VL - 110

SP - 435

EP - 448

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

IS - 509

ER -

Decoupling shrinkage and selection in bayesian linear models: A posterior summary perspective

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this