Increasing the power of specification tests

Tiemen Woutersen; Jerry A. Hausman

doi:10.1016/j.jeconom.2018.12.012

Increasing the power of specification tests

Tiemen Woutersen, Jerry A. Hausman

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

5 Scopus citations

Abstract

This paper shows how to increase the power of Hausman's (1978) specification test as well as the difference test in a large class of models. The idea is to impose the restrictions of the null and the alternative hypotheses when estimating the covariance matrix. If the null hypothesis is true then the proposed test has the same distribution as the existing ones in large samples. If the hypothesis is false then the proposed test statistic is larger with probability approaching one as the sample size increases in several important applications, including testing for endogeneity in the linear model.

Original language	English (US)
Pages (from-to)	166-175
Number of pages	10
Journal	Journal of Econometrics
Volume	211
Issue number	1
DOIs	https://doi.org/10.1016/j.jeconom.2018.12.012
State	Published - Jul 2019

Keywords

Hausman test
Power of tests
Specification test

ASJC Scopus subject areas

Economics and Econometrics

Access to Document

10.1016/j.jeconom.2018.12.012

Cite this

@article{338aa913ab794b00baae9bc2c27e6931,

title = "Increasing the power of specification tests",

abstract = "This paper shows how to increase the power of Hausman's (1978) specification test as well as the difference test in a large class of models. The idea is to impose the restrictions of the null and the alternative hypotheses when estimating the covariance matrix. If the null hypothesis is true then the proposed test has the same distribution as the existing ones in large samples. If the hypothesis is false then the proposed test statistic is larger with probability approaching one as the sample size increases in several important applications, including testing for endogeneity in the linear model.",

keywords = "Hausman test, Power of tests, Specification test",

author = "Tiemen Woutersen and Hausman, {Jerry A.}",

note = "Funding Information: We thank Donald Andrews, Miriam Arden, Xiaohong Chen, Antonio Galvao, Carter Hill, Whitney Newey, and Gary Solon for helpful discussions. We also thank seminar participants at MIT, New York University Abu Dhabi, Pennsylvania State University, and Yale University. The comments of an associate editor and two referees improved and shortened the paper and we are grateful for those. All remaining errors are our own. Publisher Copyright: {\textcopyright} 2018 Elsevier B.V.",

year = "2019",

month = jul,

doi = "10.1016/j.jeconom.2018.12.012",

language = "English (US)",

volume = "211",

pages = "166--175",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Increasing the power of specification tests

AU - Woutersen, Tiemen

AU - Hausman, Jerry A.

N1 - Funding Information: We thank Donald Andrews, Miriam Arden, Xiaohong Chen, Antonio Galvao, Carter Hill, Whitney Newey, and Gary Solon for helpful discussions. We also thank seminar participants at MIT, New York University Abu Dhabi, Pennsylvania State University, and Yale University. The comments of an associate editor and two referees improved and shortened the paper and we are grateful for those. All remaining errors are our own. Publisher Copyright: © 2018 Elsevier B.V.

PY - 2019/7

Y1 - 2019/7

N2 - This paper shows how to increase the power of Hausman's (1978) specification test as well as the difference test in a large class of models. The idea is to impose the restrictions of the null and the alternative hypotheses when estimating the covariance matrix. If the null hypothesis is true then the proposed test has the same distribution as the existing ones in large samples. If the hypothesis is false then the proposed test statistic is larger with probability approaching one as the sample size increases in several important applications, including testing for endogeneity in the linear model.

AB - This paper shows how to increase the power of Hausman's (1978) specification test as well as the difference test in a large class of models. The idea is to impose the restrictions of the null and the alternative hypotheses when estimating the covariance matrix. If the null hypothesis is true then the proposed test has the same distribution as the existing ones in large samples. If the hypothesis is false then the proposed test statistic is larger with probability approaching one as the sample size increases in several important applications, including testing for endogeneity in the linear model.

KW - Hausman test

KW - Power of tests

KW - Specification test

UR - http://www.scopus.com/inward/record.url?scp=85058778828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058778828&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2018.12.012

DO - 10.1016/j.jeconom.2018.12.012

M3 - Article

AN - SCOPUS:85058778828

SN - 0304-4076

VL - 211

SP - 166

EP - 175

JO - Journal of Econometrics

JF - Journal of Econometrics

IS - 1

ER -

Increasing the power of specification tests

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this