SOCCER / Outcome calibration

Minute-Bucket Calibration Support

Places each published minute bucket's support beside its mean forecast-outcome gap and recorded calibration error.

Derived analysis6 published rows6 fieldsDate varies or is unrecorded; see scope

Published measurements

Choose a measurement

MeasurementPopulationOrder

6 matching rows; 6 contain outcome minus forecast.

CSV includes 6 matching rows, all fields, and source context; missing values stay blank.

Measured rows: 6 / 60 unavailable
Median: 34.98 ppMiddle ranked value
Middle 50%: 34.08 pp to 42.39 pp25th to 75th percentile
Observed range: 33.69 pp to 48.24 ppMinimum to maximum

Summaries describe the filtered rows with equal row weight. Row counts are not independent game or event counts.

Measurement availability6 / 6 fields have values

Reference population: All published groups. 6 rows published.

Text search does not change this reference population.

Availability describes published values only. It does not establish data quality or independent game counts, and measurement windows can differ.

0 ppOutcome minus forecast48.24 pp

Showing 6 of 6 matching numeric rows. Open a row to inspect all its fields. Rankings apply only to the published subset.

01 / Interpretation

What this measures

Use support to judge how much each bucket contributes to the snapshot; signed gap preserves direction while the source ECE remains an absolute-error summary.

02 / Calculation

support share = bucket rows / all minute-bucket rows; signed gap = mean outcome - mean forecast

Use the table to inspect available fields and the source JSON to trace the formula inputs. CSV percentage values are stored as fractions.

03 / Population & limits

3,383 published rows across minute buckets from a 4,265-row soccer snapshot.

Rows can be repeated observations within matches. These bucket summaries are recorded calibration diagnostics, not independent samples, a causal time effect, or a performance conclusion.

04 / Source & method references

Published source JSON Gneiting & Raftery (2007), Strictly Proper Scoring Rules

References explain ingredients and prior methods. They do not validate this derived analysis or establish its originality.