Bayesian comparison of models with inequality and equality constraints

Man Suk Oh

doi:10.1016/j.spl.2013.10.005

Bayesian comparison of models with inequality and equality constraints

Man Suk Oh

Department of Statistics

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

Abstract

A Bayesian model selection procedure for comparing models subject to inequality and/or equality constraints is proposed. An encompassing prior approach is used, and a general form of the Bayes factor of a constrained model against the encompassing model is derived. A simple estimation method is proposed which can estimate the Bayes factors for all candidate models simultaneously by using one set of samples from the encompassing model. A simulation study and a real data analysis demonstrate performance of the method.

Original language	English
Pages (from-to)	176-182
Number of pages	7
Journal	Statistics and Probability Letters
Volume	84
Issue number	1
DOIs	https://doi.org/10.1016/j.spl.2013.10.005
State	Published - Jan 2014

Bibliographical note

Funding Information:
The author would like to thank a referee and an associate editor for helpful comments. This research was supported by the Basic Science Research Program though the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology ( 2010-0010285 ).

Keywords

ANOVA
Bayes factor
Multiple test
Order constraints

Access to Document

10.1016/j.spl.2013.10.005

Cite this

@article{f0327849a3e04ca2a592f5584af84ff5,

title = "Bayesian comparison of models with inequality and equality constraints",

abstract = "A Bayesian model selection procedure for comparing models subject to inequality and/or equality constraints is proposed. An encompassing prior approach is used, and a general form of the Bayes factor of a constrained model against the encompassing model is derived. A simple estimation method is proposed which can estimate the Bayes factors for all candidate models simultaneously by using one set of samples from the encompassing model. A simulation study and a real data analysis demonstrate performance of the method.",

keywords = "ANOVA, Bayes factor, Multiple test, Order constraints",

author = "Oh, {Man Suk}",

note = "Funding Information: The author would like to thank a referee and an associate editor for helpful comments. This research was supported by the Basic Science Research Program though the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology ( 2010-0010285 ).",

year = "2014",

month = jan,

doi = "10.1016/j.spl.2013.10.005",

language = "English",

volume = "84",

pages = "176--182",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Bayesian comparison of models with inequality and equality constraints

AU - Oh, Man Suk

N1 - Funding Information: The author would like to thank a referee and an associate editor for helpful comments. This research was supported by the Basic Science Research Program though the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology ( 2010-0010285 ).

PY - 2014/1

Y1 - 2014/1

N2 - A Bayesian model selection procedure for comparing models subject to inequality and/or equality constraints is proposed. An encompassing prior approach is used, and a general form of the Bayes factor of a constrained model against the encompassing model is derived. A simple estimation method is proposed which can estimate the Bayes factors for all candidate models simultaneously by using one set of samples from the encompassing model. A simulation study and a real data analysis demonstrate performance of the method.

AB - A Bayesian model selection procedure for comparing models subject to inequality and/or equality constraints is proposed. An encompassing prior approach is used, and a general form of the Bayes factor of a constrained model against the encompassing model is derived. A simple estimation method is proposed which can estimate the Bayes factors for all candidate models simultaneously by using one set of samples from the encompassing model. A simulation study and a real data analysis demonstrate performance of the method.

KW - ANOVA

KW - Bayes factor

KW - Multiple test

KW - Order constraints

UR - http://www.scopus.com/inward/record.url?scp=84887009947&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2013.10.005

DO - 10.1016/j.spl.2013.10.005

M3 - Article

AN - SCOPUS:84887009947

SN - 0167-7152

VL - 84

SP - 176

EP - 182

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

IS - 1

ER -

Bayesian comparison of models with inequality and equality constraints

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this