The effect of pseudo-exogenous instrumental variables on hausman test

Jinook Jeong, Byung Ho Yoon

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Hausman test is popularly used to examine the endogeneity of explanatory variables in a regression model. To derive a well-defined asymptotic distribution of Hausman test, the correlation between the instrumental variables and the error term needs to converge to zero. However, it is possible that there remains considerable correlation in finite samples between the instruments and the error, even though their correlation eventually converges to zero. This article investigates the potential problem that such "pseudo- exogenous" instruments may create. We show that the performance of Hausman test is deteriorated when the instruments are asymptotically exogenous but endogenous in finite samples, through Monte Carlo simulations.

Original languageEnglish
Pages (from-to)315-321
Number of pages7
JournalCommunications in Statistics: Simulation and Computation
Volume39
Issue number2
DOIs
Publication statusPublished - 2010 Feb 1

Fingerprint

Instrumental Variables
Endogeneity
Converge
Potential Problems
Zero
Error term
Asymptotic distribution
Well-defined
Regression Model
Monte Carlo Simulation

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation

Cite this

@article{850f2cdaf7204bb286c92ef29f28fa32,
title = "The effect of pseudo-exogenous instrumental variables on hausman test",
abstract = "Hausman test is popularly used to examine the endogeneity of explanatory variables in a regression model. To derive a well-defined asymptotic distribution of Hausman test, the correlation between the instrumental variables and the error term needs to converge to zero. However, it is possible that there remains considerable correlation in finite samples between the instruments and the error, even though their correlation eventually converges to zero. This article investigates the potential problem that such {"}pseudo- exogenous{"} instruments may create. We show that the performance of Hausman test is deteriorated when the instruments are asymptotically exogenous but endogenous in finite samples, through Monte Carlo simulations.",
author = "Jinook Jeong and Yoon, {Byung Ho}",
year = "2010",
month = "2",
day = "1",
doi = "10.1080/03610910903447833",
language = "English",
volume = "39",
pages = "315--321",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

The effect of pseudo-exogenous instrumental variables on hausman test. / Jeong, Jinook; Yoon, Byung Ho.

In: Communications in Statistics: Simulation and Computation, Vol. 39, No. 2, 01.02.2010, p. 315-321.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The effect of pseudo-exogenous instrumental variables on hausman test

AU - Jeong, Jinook

AU - Yoon, Byung Ho

PY - 2010/2/1

Y1 - 2010/2/1

N2 - Hausman test is popularly used to examine the endogeneity of explanatory variables in a regression model. To derive a well-defined asymptotic distribution of Hausman test, the correlation between the instrumental variables and the error term needs to converge to zero. However, it is possible that there remains considerable correlation in finite samples between the instruments and the error, even though their correlation eventually converges to zero. This article investigates the potential problem that such "pseudo- exogenous" instruments may create. We show that the performance of Hausman test is deteriorated when the instruments are asymptotically exogenous but endogenous in finite samples, through Monte Carlo simulations.

AB - Hausman test is popularly used to examine the endogeneity of explanatory variables in a regression model. To derive a well-defined asymptotic distribution of Hausman test, the correlation between the instrumental variables and the error term needs to converge to zero. However, it is possible that there remains considerable correlation in finite samples between the instruments and the error, even though their correlation eventually converges to zero. This article investigates the potential problem that such "pseudo- exogenous" instruments may create. We show that the performance of Hausman test is deteriorated when the instruments are asymptotically exogenous but endogenous in finite samples, through Monte Carlo simulations.

UR - http://www.scopus.com/inward/record.url?scp=77951069892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951069892&partnerID=8YFLogxK

U2 - 10.1080/03610910903447833

DO - 10.1080/03610910903447833

M3 - Article

AN - SCOPUS:77951069892

VL - 39

SP - 315

EP - 321

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 2

ER -