Controlling for endogeneity with instrumental variables in strategic management research
Guilhem Bascle
Additional contact information
Guilhem Bascle: HEC Paris - Recherche - Hors Laboratoire - HEC Paris - Ecole des Hautes Etudes Commerciales
Post-Print from HAL
Abstract:
This article offers a framework to understand how endogeneity arises and how to control for it with instrumental variables to estimate causal relations with observational data. It builds on the state-of-the-art research in applied and theoretical econometrics to highlight the importance of endogeneity and review the methods that can be used to address it with instrumental variables.The article also discusses when the Heckman two-step procedure can be used, as well as the tests, methods and assumptions that researchers should check when using instrumental variables.To ease implementation of the instrumental variables techniques, the author offers the STATA commands of the exposed tests and methods. Further, an empirical example is provided along with the utilized STATA codes. In the end, this article serves as a`toolkit' allowing scholars not only to understand whether endogeneity is present in their empirical setting, but also to assess the empirical validity of their work when using instrumental variables.
Keywords: endogeneity; instrumental variables; strategic management research (search for similar items in EconPapers)
Date: 2008-08
References: Add references at CitEc
Citations: View citations in EconPapers (332)
Published in Strategic Organization, 2008, Vol. 6, issue 3, p.285-327. ⟨10.1177/1476127008094339⟩
There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-00576795
DOI: 10.1177/1476127008094339
Access Statistics for this paper
More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD (hal@ccsd.cnrs.fr).