Assessing point forecast accuracy by stochastic error distance. (21st October 2017)

• Record Type: Journal Article
• Authors: Diebold, Francis X.; Shin, Minchul
• Is Part Of: Econometric reviews. Volume 36:Number 6/9(2017)
• Page Start: 588
• Page End: 598
• Publication Date: 2017-10-21
• Subjects: Absolute error loss -- forecast accuracy -- forecast evaluation -- quadratic loss -- squared error loss; C53; Econometrics -- Periodicals; 330.015195
• DOI: 10.1080/07474938.2017.1307247
• Languages: English
• ISSNs: 0747-4938

Abstract

ABSTRACT: We propose point forecast accuracy measures based directly on distance of the forecast-error c.d.f. from the unit step function at 0 ("stochastic error distance, " or SED ). We provide a precise characterization of the relationship between SED and standard predictive loss functions, and we show that all such loss functions can be written as weighted SED s. The leading case is absolute error loss. Among other things, this suggests shifting attention away from conditional-mean forecasts and toward conditional-median forecasts.