When is it justifiable to ignore explanatory variable endogeneity in a regression model?

Richard A. Ashley, Christopher Parmeter

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The point of empirical work is commonly to test a very small number of crucial null hypotheses in a linear multiple regression setting. Endogeneity in one or more model explanatory variables is well known to invalidate such testing using OLS estimation. But attempting to identify credibly valid (and usefully strong) instruments for such variables is an enterprise which is arguably fraught and invariably subject to (often justified) criticism. As a modeling step prior to such an attempt at instrument identification, we propose a sensitivity analysis which quantifies the minimum degree of correlation between these possibly-endogenous explanatory variables and the model errors which is sufficient to overturn the rejection (or non-rejection) of a particular null hypothesis at, for example, the 5% level. An application to a classic model in the empirical growth literature illustrates the practical utility of the technique.

Original languageEnglish (US)
Pages (from-to)70-74
Number of pages5
JournalEconomics Letters
Volume137
DOIs
StatePublished - Dec 1 2015

Fingerprint

Regression model
Endogeneity
Modeling
Testing
Multiple linear regression
An enterprise
Sensitivity analysis
Criticism

Keywords

  • Exogeneity
  • Instruments
  • Robustness

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance

Cite this

When is it justifiable to ignore explanatory variable endogeneity in a regression model? / Ashley, Richard A.; Parmeter, Christopher.

In: Economics Letters, Vol. 137, 01.12.2015, p. 70-74.

Research output: Contribution to journalArticle

@article{00178dfad893481bb722ff4afe8bd68e,
title = "When is it justifiable to ignore explanatory variable endogeneity in a regression model?",
abstract = "The point of empirical work is commonly to test a very small number of crucial null hypotheses in a linear multiple regression setting. Endogeneity in one or more model explanatory variables is well known to invalidate such testing using OLS estimation. But attempting to identify credibly valid (and usefully strong) instruments for such variables is an enterprise which is arguably fraught and invariably subject to (often justified) criticism. As a modeling step prior to such an attempt at instrument identification, we propose a sensitivity analysis which quantifies the minimum degree of correlation between these possibly-endogenous explanatory variables and the model errors which is sufficient to overturn the rejection (or non-rejection) of a particular null hypothesis at, for example, the 5{\%} level. An application to a classic model in the empirical growth literature illustrates the practical utility of the technique.",
keywords = "Exogeneity, Instruments, Robustness",
author = "Ashley, {Richard A.} and Christopher Parmeter",
year = "2015",
month = "12",
day = "1",
doi = "10.1016/j.econlet.2015.09.029",
language = "English (US)",
volume = "137",
pages = "70--74",
journal = "Economics Letters",
issn = "0165-1765",
publisher = "Elsevier",

}

TY - JOUR

T1 - When is it justifiable to ignore explanatory variable endogeneity in a regression model?

AU - Ashley, Richard A.

AU - Parmeter, Christopher

PY - 2015/12/1

Y1 - 2015/12/1

N2 - The point of empirical work is commonly to test a very small number of crucial null hypotheses in a linear multiple regression setting. Endogeneity in one or more model explanatory variables is well known to invalidate such testing using OLS estimation. But attempting to identify credibly valid (and usefully strong) instruments for such variables is an enterprise which is arguably fraught and invariably subject to (often justified) criticism. As a modeling step prior to such an attempt at instrument identification, we propose a sensitivity analysis which quantifies the minimum degree of correlation between these possibly-endogenous explanatory variables and the model errors which is sufficient to overturn the rejection (or non-rejection) of a particular null hypothesis at, for example, the 5% level. An application to a classic model in the empirical growth literature illustrates the practical utility of the technique.

AB - The point of empirical work is commonly to test a very small number of crucial null hypotheses in a linear multiple regression setting. Endogeneity in one or more model explanatory variables is well known to invalidate such testing using OLS estimation. But attempting to identify credibly valid (and usefully strong) instruments for such variables is an enterprise which is arguably fraught and invariably subject to (often justified) criticism. As a modeling step prior to such an attempt at instrument identification, we propose a sensitivity analysis which quantifies the minimum degree of correlation between these possibly-endogenous explanatory variables and the model errors which is sufficient to overturn the rejection (or non-rejection) of a particular null hypothesis at, for example, the 5% level. An application to a classic model in the empirical growth literature illustrates the practical utility of the technique.

KW - Exogeneity

KW - Instruments

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=84946565917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946565917&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2015.09.029

DO - 10.1016/j.econlet.2015.09.029

M3 - Article

AN - SCOPUS:84946565917

VL - 137

SP - 70

EP - 74

JO - Economics Letters

JF - Economics Letters

SN - 0165-1765

ER -