High-dimensional test for alpha in linear factor pricing models with sparse alternatives

We consider the problem of testing for the presence of alpha in Linear Factor Pricing Models. We propose a novel test of the max-of-squares type, which is designed to deal with the high dimensionality of the securities and the sparse alternatives. We rigorously show that the proposed test has attrac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of econometrics 2022-07, Vol.229 (1), p.152-175
Hauptverfasser: Feng, Long, Lan, Wei, Liu, Binghui, Ma, Yanyuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We consider the problem of testing for the presence of alpha in Linear Factor Pricing Models. We propose a novel test of the max-of-squares type, which is designed to deal with the high dimensionality of the securities and the sparse alternatives. We rigorously show that the proposed test has attractive theoretical properties and demonstrate its superior performance via Monte Carlo experiments. These results are established when the number of securities is larger than the time dimension of the return series, and the alternative hypothesis is sparse, i.e. the alpha vector is sparse. As a general alternative, we suggest to combine the max-of-squares type test and a sum-of-squares type test, to benefit from the power advantages of both tests. We apply the two proposed tests to the monthly returns on securities in the Chinese and the U.S. stock markets, respectively under the Fama–French three-factor model, and confirm the usefulness of the proposed tests in detecting the presence of alpha.
ISSN:0304-4076
1872-6895
DOI:10.1016/j.jeconom.2021.07.011