Surprisingly-early bias in forecasts for unscheduled events
Methodology
2025-12-09 v1
Abstract
When a dataset contains forecasts on unscheduled events, such as natural catastrophes, outcomes may be censored or ``hidden'' since some events have not yet occurred. This article finds that this can lead to a selection bias which affects the perceived accuracy and calibration of forecasts. This selection bias can be eliminated by excluding forecasts on outcomes which have been verified surprisingly early.
Cite
@article{arxiv.2512.07575,
title = {Surprisingly-early bias in forecasts for unscheduled events},
author = {Niklas V. Lehmann},
journal= {arXiv preprint arXiv:2512.07575},
year = {2025}
}