aucWeighted: Weighted AUC

In adamlilith/enmSdm: Tools for Modeling Niches and Distributions of Species

Weighted AUC

Description

This function calculates the area under the receiver-operator characteristic curve (AUC) following Mason & Graham (2002). Each case (presence/non-presence) can be assigned a weight, if desired.

Usage

aucWeighted(
  pres,
  contrast,
  presWeight = rep(1, length(pres)),
  contrastWeight = rep(1, length(contrast)),
  na.rm = FALSE,
  bg = NULL,
  bgWeight = NULL,
  ...
)

Arguments

pres	Vector of predictions for "positive" cases (e.g., predictions at presence sites).
contrast	Vector of predictions for "negative" cases (e.g., predictions at absence/background sites).
presWeight	Weights of positive cases. The default is to assign each positive case a weight of 1.
contrastWeight	Weights of contrast cases. The default is to assign each case a weight of 1.
na.rm	Logical. If TRUE then remove any positive cases and associated weights and contrast predictions and associated weights with NAs.
bg	Same as contrast. Included for backwards compatibility. Ignored if contrast is not NULL.
bgWeight	Same as contrastWeight. Included for backwards compatibility. Ignored if contrastWeight is not NULL.
...	Other arguments (unused).

Value

A Numeric value.

References

Mason, S.J. and N.E. Graham. 2002. Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation. Quarterly Journal of the Royal Meteorological Society 128:2145-2166. doi: 10.1256/003590002320603584

See Also

evaluate, aucMultiWeighted

Examples

pres <- seq(0.5, 1, by=0.1)
contrast <- seq(0, 1, by=0.01)

# unweighted
aucWeighted(pres, contrast)

# weighted (weight presences with low predictions more)
presWeight <- c(1, 1, 1, 0.5, 0.5, 0.5)
aucWeighted(pres, contrast, presWeight=presWeight)

# weighted (weight presences with high predictions more)
presWeight <- c(0.5, 0.5, 0.5, 1, 1, 1)
aucWeighted(pres, contrast, presWeight=presWeight)

# weight presences and absences
contrastWeight <- sqrt(contrast)
aucWeighted(pres, contrast, presWeight=presWeight, contrastWeight=contrastWeight)

adamlilith/enmSdm documentation built on Jan. 6, 2023, 11 a.m.