Probabilistic Forecasts, Calibration and Sharpness¶
Gneiting, T., Balabdaoui, F., & Raftery, A. E. (2007). Probabilistic Forecasts, Calibration and Sharpness. Journal of the Royal Statistical Society Series B: Statistical Methodology, 69(2), 243-268.
Cited by¶
4 citations across 4 artifacts.
Each citation links to the sentence it supports in the citing article.
Domain-specific¶
Mechanisms¶
- Historical or Holdout Coverage Backtest
- Its strength is that it catches the failure a point-accuracy score cannot see — bands that are confident and wrong — using only pre-outcome information, and it keeps calibration and sharpness as separate verdicts so a wide-and-useless forecast can't hide behind good coverage.
This sourceEvaluates pre-issued probabilistic forecasts against realized outcomes while judging calibration separately from sharpness, so diffuse intervals cannot earn approval from coverage alone.
- Its strength is that it catches the failure a point-accuracy score cannot see — bands that are confident and wrong — using only pre-outcome information, and it keeps calibration and sharpness as separate verdicts so a wide-and-useless forecast can't hide behind good coverage.
- Horizon Forecast-Error Trigger and Adaptation Audit
- Its strength is that it is the only mechanism that keeps the whole horizon loop honest over time, turning misses and false alarms into recalibrated margins and better indicators; sound forecast calibration
This sourceDefines forecast calibration through consistency between predictive distributions and observations, including agreement between nominal and empirical prediction-interval coverage.
- Its strength is that it is the only mechanism that keeps the whole horizon loop honest over time, turning misses and false alarms into recalibrated margins and better indicators; sound forecast calibration
- Reliability Diagram or Calibration Curve
- It says nothing about sharpness — a heuristic that always predicts the base rate can be perfectly calibrated yet useless, hugging the diagonal while making no discriminating calls — so a good-looking curve is necessary, not sufficient.
This sourceDistinguishes calibration from sharpness and shows that calibrated forecasts may remain uninformative unless predictive distributions are also sufficiently concentrated.
- It says nothing about sharpness — a heuristic that always predicts the base rate can be perfectly calibrated yet useless, hugging the diagonal while making no discriminating calls — so a good-looking curve is necessary, not sufficient.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. Neither this nor any other of the 4 citations of this work carries a recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:2fc103dbc922 · see in the full table