Nonlinear Predictability of Stock Returns? Parametric Versus Nonparametric Inference in Predictive Regressions

Bibliographic Data

ID19417618
AuthorsMatei Demetrescu (0000-0003-0815-5384, Institute for Statistics and Econometrics, Christian-Albrechts-University of Kiel, Kiel, Germany), Benjamin Hillmann (0000-0001-9292-8516, Institute for Statistics and Econometrics, Christian-Albrechts-University of Kiel, Kiel, Germany, corresponding author)
Year2022
Volume40
Issue1
Pages382-397
Publication date2022-01-02
Peer ReviewedYes
Open AccessNo
TypeARTICLE
VenueJournal of Business and Economic Statistics (JOURNAL)
Journal identifiersISSN: 0735-0015 • E-ISSN: 1537-2707
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/07350015.2020.1819821
OpenAlexW3086414500
LanguageEN
References cited35

Nonparametric test procedures in predictive regressions have χ2 limiting null distributions under both low and high regressor persistence, but low local power compared to misspecified linear predictive regressions. We argue that IV inference is better suited (in terms of local power) for analyzing additive predictive models with uncertain predictor persistence. Then, a two-step procedure is proposed for out-of-sample predictions. For the current estimation window, one first tests for predictability; in case of a rejection, one predicts using a nonlinear regression model, otherwise the historic average of the stock returns is used. This two-step approach performs better than competitors (though not by a large margin) in a pseudo-out-of-sample prediction exercise for the S&P 500

Econometrics · Inference · Machine learning · Nonparametric statistics · Parametric statistics · Predictability · Predictive power · Statistics · Computer Science · Financial Markets and Investment Strategies · Forecasting Techniques and Applications · Mathematics · Stock Market Forecasting Methods · Artificial Intelligence

Tools

Open DOI