How should we estimate value-relevance models? Insights from European Data

Onali, Enrico, Ginesti, Gianluca and Vasilakis, Chrisovalantis (2017). How should we estimate value-relevance models? Insights from European Data. British Accounting Review, 49 (5), pp. 460-473.

Abstract

We study the consequences of unobserved heterogeneity when employing different econometric methods in the estimation of two major value-relevance models: the Price Regression Model (PRM) and the Return Regression Model (RRM). Leveraging a large panel data set of European listed companies, we first demonstrate that robust Hausman tests and Breusch-Pagan Lagrange Multiplier tests are of fundamental importance to choose correctly among a fixed-effects model, a random-effects model, or a pooled OLS model. Second, we provide evidence that replacing firm fixed-effects with country and industry fixed-effects can lead to large differences in the magnitude of the key coefficients, with serious consequences for the interpretation of the effect of changes in earnings and book values per share on firm value. Finally, we offer recommendations to applied researchers aiming to improve the robustness of their econometric strategy.

Publication DOI: https://doi.org/10.1016/j.bar.2017.05.006
Divisions: Aston Business School
Additional Information: © 2017, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Uncontrolled Keywords: value-relevance,linear information model,IFRS,price regression model,return regression model,panel data,Accounting
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
Published Date: 2017-05-27
Published Online Date: 2017-05-27
Authors: Onali, Enrico ( 0000-0003-3723-2078)
Ginesti, Gianluca
Vasilakis, Chrisovalantis

Download

[img]

Version: Accepted Version

Access Restriction: Restricted to Repository staff only until 26 May 2019.

License: Creative Commons Attribution Non-commercial No Derivatives


Export / Share Citation


Statistics

Additional statistics for this record