AUCuniform {vandalico}

Calculates the uniform AUC and uniform Se*

Description

This function computes the uniform AUC (uAUC) and uniform Se* (uSe*) following Jiménez-Valverde (2022).

Usage

AUCuniform(
  mat,
  rep = 100,
  by = 0.1,
  deleteBins = NULL,
  plot = FALSE,
  plot.adds = FALSE
)

Arguments

mat

A matrix with two columns. The first column must contain the suitability values (i.e., the classification rule); the second column must contain the presences and absences.

rep

Number of sampling replications. By default, rep = 100.

by

Size of the suitability intervals (i.e., bins). By default, by = 0.1.

deleteBins

A vector (e.g., from 1 to 10 if by = 0.1) with the bins that have to be excluded (1 for [0,0.1), 10 for [0.9,1]) from the resampling procedure (trimming); NULL by default.

plot

Logical. Indicates whether or not the observed ROC curve is plotted.

plot.adds

Logical. Indicates whether or not the negative diagonal and the point of equivalence are added to the observed ROC plot.

Details

This function performs the stratified weighted bootstrap to calculate the uniform AUC (uAUC) and uniform Se* (uSe*) as suggested in Jiménez-Valverde (2022). A warning message will be shown if the sample size of any bin is zero. Another warning message will be shown if the sample size of any bin is lower than 15. In such case, trimming should be considered. The AUC (non-uniform) is estimated non-parametrically (Bamber 1975). Se* is calculated by selecting the point that minimizes the absolute difference between sensitivity and specificity and by doing the mean of those values (Jiménez-Valverde 2020).

Value

A list with the following elements:

AUC: the AUC value (non-uniform), a numeric value between 0 and 1.

Se: the Se* value (non-uniform), a numeric value between 0 and 1.

bins: a table with the sample size of each bin.

suit.sim: a matrix with the bootstrapped suitability values.

sp.sim: a matrix with the bootstrapped presence-absence data.

uAUC: a numeric vector with the (uAUC) values for each replication.

uAUC.95CI: a numeric vector with the sample (uAUC) quantiles corresponding to the probabilities 0.025, 0.5 and 0.975.

uSe: a numeric vector with the (uSe*) values for each replication.

uSe.95CI: a numeric vector with the sample (uSe*) quantiles corresponding to the probabilities 0.025, 0.5 and 0.975.

References

Bamber, D. (1975). The Area above the Ordinal Dominance Graph and the Area below the Receiver Operating Characteristic Graph. J. Math. Psychol., 12, 387-415.

Jiménez-Valverde, A. (2020). Sample size for the evaluation of presence-absence models. Ecol. Indic., 114, 106289.

Jiménez-Valverde, A. (2022). The uniform AUC: dealing with the representativeness effect in presence-absence models. Methods Ecol. Evol., accepted on 28 January 2022.

Examples

suit<-rbeta(100, 2, 2) #Generate suitability values
random<-runif(100)
sp<-ifelse(random < suit, 1, 0) #Generate presence-absence data
result<-AUCuniform(cbind(suit, sp), plot = TRUE, plot.adds = TRUE)
result$uAUC.95CI[2] #Get the uAUC