Skip to contents

Assess model performance

Source: R/assess_aeme.R
assess_aeme.Rd

Assess model performance

Usage

assess_aeme(aeme, model, var_sim)

assess_model(aeme, model, var_sim)

Arguments

aeme

Aeme object.

model

character vector; models to use. One or more of "dy_cd", "glm_aed", "gotm_wet", "simstrat_aed2". Defaults to all models if not found in aeme.

var_sim

string; of variable to plot

Value

Data frame with model performance statistics for each model and variable. These include:

  • bias - Bias

  • mae - Mean absolute error

  • rmse - Root mean square error

  • nmae - Normalised mean absolute error

  • nse - Nash-Sutcliffe efficiency

  • d2 - Index of agreement model skill score Willmott index

  • r - Pearson correlation coefficient

  • rs - Spearman correlation coefficient

  • r2 - R-squared value from linear model

  • B - Bardsley coefficient

  • n - number of observations