Research Article

Why do some probabilistic forecasts lack reliability?

National Institute of Information and Communications Technology, Tokyo 184-8795, Japan

^* Corresponding author: kubo@nict.go.jp

Received: 30 July 2018
Accepted: 16 April 2019

Abstract

In this work, we investigate the reliability of the probabilistic binary forecast. We mathematically prove that a necessary, but not sufficient, condition for achieving a reliable probabilistic forecast is maximizing the Peirce Skill Score (PSS) at the threshold probability of the climatological base rate. The condition is confirmed by using artificially synthesized forecast–outcome pair data and previously published probabilistic solar flare forecast models. The condition gives a partial answer as to why some probabilistic forecast system lack reliability, because the system, which does not satisfy the proved condition, can never be reliable. Therefore, the proved condition is very important for the developers of a probabilistic forecast system. The result implies that those who want to develop a reliable probabilistic forecast system must adjust or train the system so as to maximize PSS near the threshold probability of the climatological base rate.