Open Access
Translator Disclaimer
2018 Forecast dominance testing via sign randomization
Werner Ehm, Fabian Krüger
Electron. J. Statist. 12(2): 3758-3793 (2018). DOI: 10.1214/18-EJS1495

Abstract

We propose randomization tests of whether forecast 1 outperforms forecast 2 across a class of scoring functions. This hypothesis is of applied interest: While the prediction context often prescribes a certain class of scoring functions, it is typically hard to motivate a specific choice on statistical or substantive grounds. We investigate the asymptotic behavior of the test statistics under mild conditions, avoiding the need to assume particular dynamic properties of forecasts and realizations. The properties of the one-sided tests depend on a corresponding version of Anderson’s inequality, which we state as a conjecture of independent interest. Numerical experiments and a data example indicate that the tests have good size and power properties in practically relevant situations.

Citation

Download Citation

Werner Ehm. Fabian Krüger. "Forecast dominance testing via sign randomization." Electron. J. Statist. 12 (2) 3758 - 3793, 2018. https://doi.org/10.1214/18-EJS1495

Information

Received: 1 November 2017; Published: 2018
First available in Project Euclid: 28 November 2018

zbMATH: 06987202
MathSciNet: MR3880598
Digital Object Identifier: 10.1214/18-EJS1495

Subjects:
Primary: 62G09 , 62G10 , 62M20

Keywords: Comparative forecast evaluation , Hypothesis testing , Randomization

JOURNAL ARTICLE
36 PAGES


SHARE
Vol.12 • No. 2 • 2018
Back to Top