10,000 realizations of a ternary probability forecast, which exhibits different characteristics, depending on the realizing outcome variable. Idealized forecast example, generated as described in Wilks (2013).
data(ternary_forecast_example)A data frame with 10,000 rows and 6 variables.
forecast probability for outcome 1
forecast probability for outcome 3
outcomes, such that the forecast is well-calibrated
outcomes, such that the forecast is overconfident
outcomes, such that the forecast is underconfident
outcomes, such that the forecast is unconditionally biased
Daniel S. Wilks, 2013, The Calibration Simplex: A Generalization of the Reliability Diagram for Three-Category Probability Forecasts, Weather and Forecasting, 28, 1210-1218