nach oben

Erschienen in:

2017 | OriginalPaper | Buchkapitel

7. Causality: Endogeneity Biases and Possible Remedies

verfasst von : Willem Mertens, Amedeo Pugliese, Jan Recker

Erschienen in: Quantitative Data Analysis

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Many, if not all, studies in accounting and information systems address causal research questions. A key feature of such questions is that they seek to establish whether a variation in X (the treatment) leads to a state change in Y (the effect). These studies go beyond an association between two phenomena (i.e., a correlation between variables in the empirical model) to find a true cause-effect relationship. Moving from a simple association to a causal claims requires meeting a number of conditions.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Analyzing Longitudinal and Panel Data

Nächstes Kapitel How to Start Analyzing, Test Assumptions and Deal with that Pesky p-Value

Editors and reviewers are increasingly aware of the issues with observational data and causal claims. Some of the leading journals in business and management fields suggest that authors deal with endogeneity issues in the manuscript prior to the first submission of the study for consideration: http://strategicmanagement.net/pdfs/smj-guidelines-regarding-empirical-research.pdf

If a researcher could measure managerial skill with any confidence, the OCV would become observable. By adding it as a covariate to the OLS model specification, the estimation would be freed from the biasing effect of managerial skill.

Chapter 6 on approaches to longitudinal and panel data illustrates some additional remedies.

A note of caution is warranted here. Even though OLS regression using cross-sectional data is not the best tool and setting in which to rule out endogeneity concerns, in certain circumstances researchers can still minimize endogeneity issues and rule out sources of concerns [19]. A note of thanks goes to Stefano Cascino for highlighting this sometimes hidden truth.

Data and codes are available upon request from authors and will be available on the book’s companion website.

IVE also helps in solving measurement error problems that are due to the inability to observing and measure the best proxy for the underlying concept.

The portion of X (Inst) that is non-overlapping with Inst (X) is likely to be endogenous (uncorrelated with Y), so both must not be employed in estimating the outcome model.

The Hausman test is employed in many contexts to compare the magnitude and significance of a series of coefficients. The Hausman test is discussed in Chap. 6 to compare the results of fixed-effects and random-effects model estimation.

The econometrics literature offers rich guidance in terms of the F-test values that should be used as a benchmark: If the number of instruments is 1, 2, or more than 5, the corresponding lower threshold of F-values are 8.96, 11.59, or higher than 15 to rule out the risk of a weak instrument.

Statistical software (e.g. STATA, R, SAS) offers convenient routines with which to estimate 2SLS models.

This example is reported in Murnane and Willet [3] in much more detail. We refer the reader directly to this valuable source for an in-depth assessment and understanding of the example.

All of the issues raised in this chapter follow in the realm of a frequentist parametric framework. Other methods, including non-parametric methods, have been employed to minimize the potential issues with self-selection that are due to unobservables. For instance, Bayesian approaches have been suggested to evaluate treatment effects when selections are based on unobservables. A note of caution is required, given the limited applications of such an approach in the accounting (and finance) literature and because of the lack of evidence on the advantages of this approach over a frequentist approach.

Angrist JD, Pischke JS (2008) Mostly harmless econometrics: an empiricist’s companion. Princeton University Press, Princeton, NJ

Iyengar RJ, Zampelli EM (2009) Self-selection, endogeneity, and the relationship between CEO duality and firm performance. Strategic Manage J 30:1092–1112CrossRef

Murnane R, Willett J (2010) Methods matter. Oxford University Press, Oxford

Runkel P, McGrath JE (1972) Research on human behavior: a systematic guide to method. Holt, Rinehart and Winston, New York

Wooldridge JM (2009) Introductory econometrics: a modern approach. South-Western Cengage Learning, Mason, OH

Libby R, Bloomfield R, Nelson MW (2002) Experimental research in financial accounting. Account Org Soc 27(8):775–810CrossRef

Gassen J (2014) Causal inference in empirical archival financial accounting research. Account Org Soc 39(7):535–544CrossRef

Morgan SL, Winship C (2007) Counterfactuals and causal analysis: methods and principles for social research. Cambridge University Press, New York

Rosenbaum PR, Rubin DB (1985) Constructing a control group using multivariate matched sampling methods that incorporate the propensity score. Am Stat 39(1):33–38

10.

Certo ST, Busenbark JR, Woo H-S, Semadeni M (2016) Sample selection bias and Heckman models in strategic management research. Strategic Manage J. doi:10.1002/smj.2475

11.

Semadeni M, Withers MC, Certo ST (2014) The perils of endogeneity and instrumental variables in strategic research: understanding through simulations. Strategic Manage J 35(7):1070–1079CrossRef

12.

Kennedy P (2003) A guide to econometrics. MIT Press, Cambridge, MA

13.

Maddala G (1991) A perspective on the use of limited-dependent and qualitative variables models in accounting research. Account Rev 66(4):788–807

14.

Lennox CS, Francis JR, Wang Z (2011) Selection models in accounting research. Account Rev 87(2):589–616CrossRef

15.

Larcker DF, Rusticus TO (2007) Endogeneity and empirical accounting research. Eur Account Rev 16(1):207–215CrossRef

16.

Chenhall RH, Moers F (2007) The issue of endogeneity within theory-based, quantitative management accounting research. Eur Account Rev 16(1):173–196CrossRef

17.

Schroeder DA (2010) Accounting and causal effects. Econometric challenges 5. Springer Science & Business Media, Berlin

18.

Antonakis J, Bendahan S, Jacquart P, Lalive R (2010) On making causal claims: a review and recommendations. Leadersh Q 21:1086–1120CrossRef

19.

Roberts MR, Whited TM (2013) Endogeneity in empirical corporate finance, Handbook of the economics of finance. Elsevier, Amsterdam, pp 493–572

20.

Larcker DF, Rusticus TO (2010) On the use of instrumental variables in accounting research. J Account Econ 49(3):186–205CrossRef

21.

Tucker JW (2010) Selection bias and econometric remedies in accounting and finance research. J Account Lit 29:31–57

22.

Hamilton BH, Nickerson JA (2003) Correcting for endogeneity in strategic management research. Strategic Org 1:51–78CrossRef

23.

Bascle G (2008) Controlling for endogeneity with instrumental variables in strategic management research. Strategic Org 6:285–327CrossRef

24.

Li M (2013) Using the propensity score method to estimate causal effects: a review and practical guide. Org Res Methods 16:188–226CrossRef

25.

Gippel J, Smith T, Zhu Y (2015) Endogeneity in accounting and finance research: natural experiments as a state-of-the-art solution. Abacus 51(2):143–168CrossRef

26.

Armstrong CS, Core JE, Guay WR (2014) Do independent directors cause improvements in firm transparency? J Financ Econ 113:383–403CrossRef

27.

Lennox CS, Wu X, Zhang T (2014) Does mandatory rotation of audit partners improve audit quality? Account Rev 89(5):1775–1803CrossRef

28.

Heckman J (1979) Sample selection bias as a specification error. Econometrica 47(1):53–161CrossRef

29.

National Education Longitudinal Study 1988. https://nces.ed.gov/surveys/nels88/index.asp

30.

Gow ID, Larcker DF, Reiss PC (2015) Causal inference in accounting research. Working Paper

Titel: Causality: Endogeneity Biases and Possible Remedies
verfasst von: Willem Mertens
Amedeo Pugliese
Jan Recker
Verlag: Springer International Publishing
Buch: Quantitative Data Analysis
Print ISBN: 978-3-319-42699-0

Electronic ISBN: 978-3-319-42700-3

Copyright-Jahr: 2017
DOI: https://doi.org/10.1007/978-3-319-42700-3_7

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"