kuenm_proc: Partial ROC calculation for ecological niche models

In manubio13/ku.enm: Detailed development of ecological niche models using Maxent

Partial ROC calculation for ecological niche models

Description

kuenm_proc applies partial ROC tests to model predictions.

Usage

kuenm_proc(occ.test, model, threshold = 5, rand.percent = 50,
           iterations = 500, parallel = FALSE)

Arguments

occ.test	matrix, data.frame, or numeric vector containing coordinates of occurrences to test model predictions to be evaluated. If matrix or data.frame, columns must include longitude and latitude in that order. If numeric, values of suitability in such occurrences. If a matrix or a data.frame is provided, model must be a RasterLayer.
model	RasterLayer or numeric vector of ecological niche model predictions to be evaluated. If RasterLayer, layer of predicted suitability. If numeric vector, predicted suitability values.
threshold	(numeric) value from 0 to 100 to represent the percentage of potential error (E) that the data could have due to any source of uncertainty. Default = 5.
rand.percent	(numeric) percentage of testing data to be used in each bootstrapped process for calculating the partial ROC. Default = 50.
iterations	(numeric) number of bootstrap iterations to be performed; default = 500.
parallel	(logical) argument deprecated. Default = NULL.

Details

Partial ROC is calculated following Peterson et al. (2008; http://dx.doi.org/10.1016/j.ecolmodel.2007.11.008).

Value

A list with the summary of the results and a data.frame containing the AUC values and AUC ratios calculated for all iterations.

Examples

data("sp_test", package = "kuenm")
model <- raster::raster(system.file("extdata/sp_model.tif",
                                       package = "kuenm"))
thres <- 5
rand_perc <- 50
iterac <- 500

p_roc <- kuenm_proc(occ.test = sp_test, model = model, threshold = thres,
                   rand.percent = rand_perc, iterations = iterac)

manubio13/ku.enm documentation built on Jan. 5, 2024, 5:55 a.m.