Leader Forecast Calibration Score
interval score (interval width + coverage-miss penalty) + 80/90 interval hit rates vs nominal coverage
Leader Forecast Calibration
Individual · — · Interval-score / hit-rate scoring against actuals (proposed)
→ Read the Handbook entry for Leader Forecast Calibration — its measures, the owned Principia rendering, and the evidence.
Definition
Subcomponent (b) of Leader Forecasting Accuracy: interval honesty — do a leader's stated uncertainty intervals contain actuals at their nominal rate (e.g., 90% intervals covering ~90% of actuals)? Scored with the Brier / interval-score family (interval width penalty + miss penalty; hit rates vs nominal coverage). Distinct from point accuracy. Proposed PA-original construct (provenance: pa-original); psychometric properties unestablished.
Also known as: Forecast Calibration · Interval Honesty
Instruments measuring this construct
No instruments linked to this construct yet.
Instruments link to constructs via instrument.constructs_covered[]; this rail fills as the curator promotes new rows.
Operational metrics for this construct
Top effect-size relations
No effect-size rows tied to this construct yet. EffectSize ingest is staged behind the curator-promotion CLI; this rail fills as rows land. Ranking: |value| × quality-grade weight.
Interventions targeting this construct
No interventions in the registry currently target this construct. The intervention library (PRN-047) fills as the curator promotes new rows from the applied organizational-development literature.
Citations
No citations explicitly link to this construct yet.