Fixed-Effects in Empirical Accounting Research

51 Pages Posted: 23 Jul 2015 Last revised: 6 Mar 2016

See all articles by Eli Amir

Eli Amir

Tel Aviv University

Jose M. Carabias

London School of Economics & Political Science (LSE) - Department of Economics

Jonathan Jona

University of Melbourne - Department of Accounting and Business Information Systems

Gilad Livne

University of Exeter Business School

Date Written: March 4, 2016

Abstract

The fixed-effects specification is often used in panel datasets as a way of dealing with correlated omitted variables. A review of recent accounting publications reveals that while researchers are generally aware of the need to include fixed-effects in empirical models when using panel datasets (firm-time observations), many chose to replace firm fixed-effects with other form of fixed-effects, mainly industry fixed-effects. We examine the consequences of using different model specifications and show analytically and using simulations that replacing firm fixed or omitting them can lead to biased estimates and wrong inferences. To illustrate the importance of properly including firm fixed-effects, we reexamine commonly used regression models in the accounting literature. We show how inferences change when fixed-effects are properly included. Importantly, we identify circumstances where the fixed-effects specification is likely to fail and offer a full differencing model as an alternative specification.

Keywords: Fixed effects, Estimation methods, Simulations

Suggested Citation

Amir, Eli and Carabias, Jose M. and Jona, Jonathan and Livne, Gilad, Fixed-Effects in Empirical Accounting Research (March 4, 2016). Available at SSRN: https://ssrn.com/abstract=2634089 or http://dx.doi.org/10.2139/ssrn.2634089

Eli Amir (Contact Author)

Tel Aviv University ( email )

312 Recanati Bldg.
69978 Tel Aviv
Israel
+972 3 640-8510 (Phone)
+972 3 640-7738 (Fax)

Jose M. Carabias

London School of Economics & Political Science (LSE) - Department of Economics ( email )

Houghton Street
London WC2A 2AE
United Kingdom

Jonathan Jona

University of Melbourne - Department of Accounting and Business Information Systems ( email )

198 Berkeley Street
Level 7
Melbourne, Victoria 3010 3010
Australia

Gilad Livne

University of Exeter Business School ( email )

Streatham Court
Rennes Drive
Exeter, EX4 4JH
United Kingdom
+44(0)1392 724436 (Phone)

Register to save articles to
your library

Register

Paper statistics

Downloads
716
Abstract Views
2,507
rank
34,145
PlumX Metrics