Package index • modelskill

Point-prediction evaluation

Continuous-prediction error, association, agreement, and efficiency metrics.

model_metrics(): Calculate prediction-validation metrics for one or more models
bias(): Mean error (ME) of quantitative predictions
mae(): Mean absolute error
mse(): Mean squared error
rmse(): Root mean squared error
mdae(): Median absolute error
nrmse(): Normalized root mean squared error
crmse(): Centered root mean squared error
rrmse(): Relative root mean squared error
rae(): Relative absolute error
correlation(): Pearson correlation
r2(): Squared Pearson correlation
R2(): Model-efficiency R-squared
nse(): Nash-Sutcliffe efficiency
mec(): Model efficiency coefficient
sd_ratio(): Prediction-to-observation standard deviation ratio
ccc(): Lin's concordance correlation coefficient
willmott_d(): Willmott's index of agreement
rpd(): Ratio of performance to deviation
rpiq(): Ratio of performance to interquartile distance
rer(): Range-to-RMSE ratio
sep(): Standard error of prediction
mape(): Mean absolute percentage error
mpe(): Mean percentage error
smape(): Symmetric mean absolute percentage error
msle(): Mean squared logarithmic error
rmsle(): Root mean squared logarithmic error
pinball_loss(): Quantile (pinball) loss
kge(): Kling-Gupta efficiency: KGE (2009)

Interval, quantile, and full-distribution calibration and scoring diagnostics.

Integrated graphical diagnostics for prediction and map quality.