Download This PaperDoes Unobservable Heterogeneity Matter for Portfolio-Based Asset Pricing Tests?
156 Pages Posted: 4 Jun 2018 Last revised: 20 Feb 2024
There are 2 versions of this paper
Does Unobservable Heterogeneity Matter for Portfolio-Based Asset Pricing Tests?
Generalized Portfolio Sorts for Factor Validation
Date Written: September 12, 2024
Abstract
We show that portfolio sorts often misattribute cross-sectional return predictability to the firm characteristic underlying the sort. This misattribution occurs when the sorting variable correlates with a firm-specific effect that captures unobservable heterogeneity across firms. We propose a new, firm-level regression approach that reproduces the results from portfolio sorts as a special case, handles multivariate firm characteristics, and can control for unobservable heterogeneity across firms. Empirical tests show that nearly half of the firm characteristics in Gu et al. (2020, 2021), that predict the cross-section of stock returns in portfolio sorts, lose their predictive power when unobservable heterogeneity is considered.
Keywords: : Portfolio sorts, Cross-section of expected returns, Tests of asset pricing models, Random effects assumption
JEL Classification: C21, G14, D1
Suggested Citation: Suggested Citation
Markus Schmid
University of St. Gallen - Swiss Institute of Banking and Finance ( email )
Unterer Graben 21
St. Gallen, 9000
Switzerland
University of St. Gallen - School of Finance ( email )
Unterer Graben 21
St.Gallen, CH-9000
Switzerland
Swiss Finance Institute
c/o University of St. Gallen
Dufourstrassse 50
St. Gallen, SG 9000
Switzerland
European Corporate Governance Institute (ECGI) ( email )
c/o the Royal Academies of Belgium
Rue Ducale 1 Hertogsstraat
1000 Brussels
Belgium