'Choosing Factors' by Fama and French (2018): A Comment

32 Pages Posted: 9 Dec 2018

See all articles by David E. Allen

David E. Allen

School of Mathematics and Statistics, The University of Sydney; Financial Research Network (FIRN); Department of Finance; School of Business and Law, Edith Cowan University

Michael McAleer

Erasmus University Rotterdam - Erasmus School of Economics, Econometric Institute; Tinbergen Institute; University of Tokyo - Centre for International Research on the Japanese Economy (CIRJE), Faculty of Economics

Date Written: November 15, 2018

Abstract

This paper features a statistical analysis of the monthly three factor Fama/French return series. We apply rolling OLS regressions to explore the relationship between the 3 factors, using monthly data from July 1926 to June 2018, that are available on Ken French's website. The results suggest there are significant and time varying relationships between the factors. We then switch to a sub-sample from July 1990 to July 2018, also taken from Ken French's website. The three series and their inter-relationships are analysed using two stage least squares and the Hausman test to check for issues related to endogeneity, the Sargan over-identification test and the Cragg-Donald weak instrument test. The relaationship between factors is also examined using OLS incorporating Ramsey's RESET tests of functional form misspecification, plus Naradaya-Watson kernel regression techniques. The empirical results suggest that the factors, when combined in OLS regression analysis, as suggested by Fama and French (2018), are likely to suffer from endogeneity. OLS regression analysis and the the application of Ramsey's RESET tests suggest a non-linear relationship exists between the three series, in which squared and cubed terms are significant. This non-linearity is also confirmed by the Kernel regression analysis. We use two instruments to estimate the market betas, and then use the factor estimates in a second set of panel data tests using a small sample of monthly returns for US firms that are drawn from the on-line data source “tingo”. These issues are analysed using methods suggested by Petersen (2009) to permit clustering in the panels by date and firm. The empirical results suggest that using an instrument to capture endogeneity reduces the standard error of market beta in subsequent cross-sectional tests, but that clustering effects, as suggested by Petersen (2009), will also impact on the estimated standard errors. The empirical results suggest that using these factors in linear regression analysis, such as suggested by Fama and French (2018), as a method of screening factor relevance, is problematic in that the estimated standard errors are highly sensitive to the correct model specification.

Keywords: Fama-French Factors, Correct specification, Ramsey's RESET, Hausman tests, Endogeneity, Consistent standard errors

JEL Classification: C13, C14, G12

Suggested Citation

Allen, David Edmund and McAleer, Michael, 'Choosing Factors' by Fama and French (2018): A Comment (November 15, 2018). Available at SSRN: https://ssrn.com/abstract=3272608 or http://dx.doi.org/10.2139/ssrn.3272608

David Edmund Allen (Contact Author)

School of Mathematics and Statistics, The University of Sydney ( email )

School of Mathematics and Statistics F07
University of Sydney
Sydney, New South Wales 2006
Australia

HOME PAGE: http://www.maths.usyd.edu.au

Financial Research Network (FIRN)

C/- University of Queensland Business School
St Lucia, 4071 Brisbane
Queensland
Australia

HOME PAGE: http://www.firn.org.au

Department of Finance ( email )

Taiwan
Taiwan

School of Business and Law, Edith Cowan University

100 Joondalup Drive
Joondalup, WA 6027
Australia

HOME PAGE: http://www.dallenwapty.com

Michael McAleer

Erasmus University Rotterdam - Erasmus School of Economics, Econometric Institute ( email )

Rotterdam
Netherlands

Tinbergen Institute

Rotterdam
Netherlands

University of Tokyo - Centre for International Research on the Japanese Economy (CIRJE), Faculty of Economics

Tokyo
Japan

Register to save articles to
your library

Register

Paper statistics

Downloads
89
Abstract Views
380
rank
282,149
PlumX Metrics