areModelsDominated {hydromad}R Documentation

Are Models Dominated?

Description

Identify dominated model realisations, that are inferior to another model in all simulation periods.

Usage

areModelsDominated(res, objectives = "r.squared")

Arguments

res

data.frame of results, including the column sim.period and the columns named in objectives. At least one of the following column names should be included as id variables: Model.str,Catchment,calib.period,Cal.objfn Other columns will be ignored.

objectives

Vector of column names containing performance measures. We assume higher values are better. Values should be transformed prior to use.

Details

The data.frame of results res is transformed to wide format with a column for performance in each sim.period for each of the objectives. Each row is interpreted as a candidate model realisation. The resulting matrix is filtered using paretoFilter to identify dominated models.

Value

A wide-format data.frame with id variable columns, a column for each sim.period value, and a column dominated indicating whether another model is better in all simulation periods.

Author(s)

Joseph Guillaume

See Also

paretoFilter, paretoCatchments

Examples


data(YeAl97)

## Dataset consisting of results for two simulation periods,
##  obtained by calibration in the same periods with different
##  model structures.
results <- subset(YeAl97,Catchment=="Salmon")

## Table indicating whether models defined by their
##  calib.period and Model.str are dominated according
##  to the objective E
areModelsDominated(results,objectives="E")
[Package hydromad version 0.9-18 Index]