How Robust are Empirical Factor Models to the Choice of Breakpoints?

Quarterly Journal of Finance, forthcoming

72 Pages Posted: 20 Sep 2021 Last revised: 7 Aug 2023

See all articles by Fabian Hollstein

Fabian Hollstein

Saarland University

Marcel Prokopczuk

Leibniz Universität Hannover - Faculty of Economics and Management; University of Reading - ICMA Centre

Victoria Voigts

Leibniz Universität Hannover - Faculty of Economics and Management

Date Written: September 16, 2021

Abstract

We comprehensively investigate the robustness of well-known factor models to altered factor formation breakpoints. Deviating from the standard 30th and 70th percentile selection, we use an extensive set of anomaly test portfolios to uncover two main findings: First, there is a trade-off between specification and diversification. More centered breakpoints tend to result in less (idiosyncratic) risk. More extreme sorts lead to greater exposure to the underlying anomalies and thus to higher average returns. Second, the models are robust to varying degrees. The Hou, Xue, and Zhang (2015) model is much more sensitive to changes in breakpoints than the Fama–French models.

Keywords: Asset Pricing, Factors, Replication, Breakpoint Analysis, Robustness

JEL Classification: G12, C58, G10

Suggested Citation

Hollstein, Fabian and Prokopczuk, Marcel and Voigts, Victoria, How Robust are Empirical Factor Models to the Choice of Breakpoints? (September 16, 2021). Quarterly Journal of Finance, forthcoming, Available at SSRN: https://ssrn.com/abstract=3924821 or http://dx.doi.org/10.2139/ssrn.3924821

Fabian Hollstein

Saarland University ( email )

Campus
Saarbrucken, Saarland D-66123
Germany

Marcel Prokopczuk

Leibniz Universität Hannover - Faculty of Economics and Management ( email )

Koenigsworther Platz 1
Hannover, 30167
Germany

University of Reading - ICMA Centre ( email )

Whiteknights Park
P.O. Box 242
Reading RG6 6BA
United Kingdom

Victoria Voigts (Contact Author)

Leibniz Universität Hannover - Faculty of Economics and Management ( email )

Koenigsworther Platz 1
Hannover, 30167
Germany

HOME PAGE: http://https://www.fcm.uni-hannover.de/de/institut/team/homepages/victoria-voigts/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
502
Abstract Views
1,186
Rank
102,005
PlumX Metrics