Distributional regression and its evaluation with the CRPS: Bounds and convergence of the minimax risk - Archive ouverte HAL Access content directly
Journal Articles International Journal of Forecasting Year : 2023

Distributional regression and its evaluation with the CRPS: Bounds and convergence of the minimax risk

Régression distributionnelle et son évaluation avec le CRPS: Bornes et convergence du risque minimax

Abstract

The theoretical advances on the properties of scoring rules over the past decades have broadened the use of scoring rules in probabilistic forecasting. In meteorological forecasting, statistical postprocessing techniques are essential to improve the forecasts made by deterministic physical models. Numerous state-of-the-art statistical postprocessing techniques are based on distributional regression evaluated with the Continuous Ranked Probability Score (CRPS). However, theoretical properties of such evaluation with the CRPS have solely considered the unconditional framework (i.e. without covariates) and infinite sample sizes. We extend these results and study the rate of convergence in terms of CRPS of distributional regression methods. We find the optimal minimax rate of convergence for a given class of distributions and show that the k-nearest neighbor method and the kernel method reach this optimal minimax rate.
Fichier principal
Vignette du fichier
1-s2.0-S0169207022001443-main.pdf (403.57 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03662994 , version 1 (09-05-2022)
hal-03662994 , version 2 (03-11-2022)
hal-03662994 , version 3 (24-02-2023)
hal-03662994 , version 4 (24-10-2023)

Licence

Identifiers

Cite

Romain Pic, Clément Dombry, Philippe Naveau, Maxime Taillardat. Distributional regression and its evaluation with the CRPS: Bounds and convergence of the minimax risk. International Journal of Forecasting, 2023, 39 (4), pp.1564-1572. ⟨10.1016/j.ijforecast.2022.11.001⟩. ⟨hal-03662994v4⟩
202 View
119 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More