On testing equal conditional predictive ability under measurement error

• Verfasst von: Hoga, Yannick [VerfasserIn]
• Verfasst von: Dimitriadis, Timo [VerfasserIn]
• Titel: On testing equal conditional predictive ability under measurement error
• Verf.angabe: Yannick Hoga and Timo Dimitriadis
• Jahr: 2023
• Umfang: 13 S.
• Fussnoten: Online veröffentlicht am 3. Februar 2022 ; Gesehen am 01.08.2023
• Titel Quelle: Enthalten in: Journal of business & economic statistics
• Ort Quelle: Abingdon : Taylor & Francis, 1983
• Jahr Quelle: 2023
• Band/Heft Quelle: 41(2023), 2, Seite 364-376
• ISSN Quelle: 1537-2707
• DOI: doi:10.1080/07350015.2021.2021923
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Equal predictive ability
• Sach-SW: Forecasting
• Sach-SW: Hypothesis testing
• Sach-SW: Measurement error
• Form-SW: Aufsatz in Zeitschrift
• K10plus-PPN: 185405161X

Abstract

Loss functions are widely used to compare several competing forecasts. However, forecast comparisons are often based on mismeasured proxy variables for the true target. We introduce the concept of exact robustness to measurement error for loss functions and fully characterize this class of loss functions as the Bregman class. Hence, only conditional mean forecasts can be evaluated exactly robustly. For such exactly robust loss functions, forecast loss differences are on average unaffected by the use of proxy variables and, thus, inference on conditional predictive ability can be carried out as usual. Moreover, we show that more precise proxies give predictive ability tests higher power in discriminating between competing forecasts. Simulations illustrate the different behavior of exactly robust and nonrobust loss functions. An empirical application to U.S. GDP growth rates demonstrates the nonrobustness of quantile forecasts. It also shows that it is easier to discriminate between mean forecasts issued at different horizons if a better proxy for GDP growth is used.