Developed by Glenn W. Brier (Verification of Forecasts Expressed in Terms of Probability, 1950), with the decomposition by Allan H. Murphy (A New Vector Partition of the Probability Score, 1973).
Scores probability forecasts by the squared gap between the stated chance and what happened, rewarding honest calibration and splitting skill into reliability and resolution.
When to reach for it
When a team makes repeated probability forecasts and needs to know who is calibrated, which method works, and whether skill is improving.
How it runs
- Write each question with a clear way to resolve it and a date.
- Record the forecast probability.
- At resolution, record one if it happened, zero if not.
- Score each forecast as the squared difference.
- Average across forecasts, and decompose the result.
- Compare with an always-base-rate forecaster and with peers.
Where it sits in SOLVE eX
Go to the source
- Verification of Forecasts Expressed in Terms of Probability, Monthly Weather Review, 1950
- A New Vector Partition of the Probability Score, 1973