Project score data for “public project”

    Project: public project

    Scores (all models)

    Name Description Last Update # Score Values
    Absolute Error The absolute value of the truth value minus the model's point estimate. Lower is better. Dec. 3, 2019, 12:30 a.m. 4
    Error The the truth value minus the model's point estimate. Dec. 3, 2019, 12:30 a.m. 4
    Log score (multi bin) This is calculated by finding the natural log of probability assigned to the true and a few neighbouring bins. Higher is better. Dec. 3, 2019, 12:30 a.m. 4
    Log score (single bin) Natural log of probability assigned to the true bin. Higher is better. Dec. 3, 2019, 12:30 a.m. 4
    Probability Integral Transform (PIT) The probability integral transform (PIT) is a metric commonly used to evaluate the calibration of probabilistic forecasts. Dec. 3, 2019, 12:30 a.m. 4
    (Cached file updated 2019-12-07 04:00:56)

    Score Counts (per model)

    Model Score # Score Values
    Test ForecastModel1 (public) Absolute Error 4
    Test ForecastModel1 (public) Error 4
    Test ForecastModel1 (public) Log score (multi bin) 4
    Test ForecastModel1 (public) Log score (single bin) 4
    Test ForecastModel1 (public) Probability Integral Transform (PIT) 4