Calculate a suite of performance metrics on either crossvalidation, external validation data or (at your own risk) in-sample validation.
PerformanceMeasures(.model, .ras, threshold = NULL)
.model is list of a data frame (data) and a model object (model). .model is passed automatically in workflow, combining data from the model module(s) and process module(s), to the output module(s) and should not be passed by the user..ras is a raster layer, brick or stack object. .ras is passed automatically in workflow from the covariate module(s) to the output module(s) and should not be passed by the user.This model prints to console a number of metrics of the model fitted:
auc - (see ?SDMTools::auc) The Area Under the Curve of the Receiver operating characteristic using a Mann-Whitney U statistic
kappa - (see ?kappa) An estimate of the 2-norm condition number of a matrix or of the R matrix of a QR decomposition, perhaps of a linear fit. The 2-norm condition number can be shown to be the ratio of the largest to the smallest non-zero singular value of the matrix.
omissions - (see ?SDMTools::omission) The ommission rate as a proportion of true occurrences misidentified given the defined threshold value.
sensitivity - (see ?SDMTools::sensitivity) The proportion of actual presences predicted given the defined threshold value.
specificity - (see ?SDMTools::specificity) The proportion of actual absences predicted given the defined threshold value.
proportionCorrect - (see ?SDMTools::prop.correct) The proportion of the presence and absence records correctly identified given the defined threshold value.
1.0
2016-06-15
presence/absence, presence/background
Other output: Appify,
InteractiveCovariateMap,
InteractiveMap, NoOutput,
PredictNewRasterMap,
PrintMap, ROCcurve,
ResponseCurveViz,
ResponseCurve,
SameTimePlaceMap, SeparatePA,
SurfaceMap,
VariableImportance