Local proper scoring rules of order two

TL;DR

This paper characterizes local proper scoring rules of order two for probabilistic forecasts, providing a theoretical foundation and demonstrating their application in weather forecast evaluation.

Contribution

It offers a new characterization of second-order local proper scoring rules, expanding the theoretical understanding and practical application in forecast assessment.

Findings

Characterization of local proper scoring rules of order two

Application to weather forecast evaluation

Comparison of local and nonlocal scoring rules

Abstract

Scoring rules assess the quality of probabilistic forecasts, by assigning a numerical score based on the predictive distribution and on the event or value that materializes. A scoring rule is proper if it encourages truthful reporting. It is local of order $k$ if the score depends on the predictive density only through its value and the values of its derivatives of order up to $k$ at the realizing event. Complementing fundamental recent work by Parry, Dawid and Lauritzen, we characterize the local proper scoring rules of order 2 relative to a broad class of Lebesgue densities on the real line, using a different approach. In a data example, we use local and nonlocal proper scoring rules to assess statistically postprocessed ensemble weather forecasts.