Predictive Ability Tests with Possibly Overlapping Models

42 Pages Posted: 6 Mar 2023 Last revised: 20 Feb 2024

See all articles by Valentina Corradi

Valentina Corradi

University of Surrey - School of Economics

Jack Fosten

King’s College London - King's Business School

Daniel Gutknecht

Goethe University Frankfurt

Date Written: February 8, 2024

Abstract

This paper provides novel tests for comparing out-of-sample predictive ability of two or more competing models that are possibly overlapping. The tests do not require pre-testing, they allow for dynamic misspecification and are valid under different estimation schemes and loss
functions. In pairwise model comparisons, the test is constructed by adding a random perturbation to both the numerator and denominator of a standard Diebold-Mariano test statistic. This prevents degeneracy in the presence of overlapping models but becomes asymptotically negligible otherwise. The test is shown to control the Type I error probability asymptotically at the nominal level, uniformly over all null data generating processes. A similar idea is used to develop a superior predictive ability test for the comparison of multiple models against a benchmark. Monte Carlo simulations demonstrate that our tests exhibit very good size control in finite samples reducing both over- and under-rejection relative to its competitors. Finally, an application to forecasting U.S. excess bond returns provides evidence in favour of models using macroeconomic factors.

Keywords: degeneracy, uniform inference, block bootstrap, out-of-sample evaluation, excess bond returns

JEL Classification: C12, C22, C53

Suggested Citation

Corradi, Valentina and Fosten, Jack and Gutknecht, Daniel, Predictive Ability Tests with Possibly Overlapping Models (February 8, 2024). Available at SSRN: https://ssrn.com/abstract=4375650 or http://dx.doi.org/10.2139/ssrn.4375650

Valentina Corradi

University of Surrey - School of Economics ( email )

Guildford
Guildford, Surrey GU2 5XH
United Kingdom

Jack Fosten

King’s College London - King's Business School ( email )

150 Stamford Street
London, SE1 9NH
United Kingdom

Daniel Gutknecht (Contact Author)

Goethe University Frankfurt ( email )

Frankfurt am Main, 60629
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
192
Abstract Views
505
Rank
297,090
PlumX Metrics