modEvA3.41 package

Model Evaluation and Analysis

applyThreshold

Apply threshold(s) to model predictions

arrangePlots

Arrange plots

AUC

Area Under the Curve

Boyce

Boyce Index

confusionLabel

Label predictions according to their confusion matrix category

confusionMatrix

Confusion matrix

Dsquared

Explained deviance

errorMeasures

Measures of model prediction error.

evaluate

Evaluate a model based on the elements of a confusion matrix.

evenness

Evenness in a binary vector.

getBins

Get bins of continuous values.

getModEqn

Get model equation

getThreshold

Prediction threshold for a given criterion

HLfit

Hosmer-Lemeshow goodness of fit

inputMunch

Munch inputs into 'obs' and 'pred' vectors

logLike

Log-likelihood

lollipop

Lollipop chart

MESS

Multivariate Environmental Similarity Surfaces based on a data frame

MillerCalib

Miller's calibration satistics for logistic regression models

mod2obspred

Extract observed and predicted, or predictor, values from a model obje...

modEvA-package

Model Evaluation and Analysis

modEvAmethods

Methods implemented in modEvA functions

multModEv

Multiple model evaluation

OA

Overlap Analysis

optiPair

Optimize the classification threshold for a pair of related model eval...

optiThresh

Optimize threshold for model evaluation.

plotCoeffs

Plot model coefficients with confidence intervals

plotGLM

Plot a generalized linear model

predDensity

Plot the density of predicted or predictor values for presences and ab...

predPlot

Plot predicted values for presences and absences, optionally classifie...

prevalence

Prevalence

pseudoRsq

Pseudo-R-squared measures for binary-response models

ptsrast2obspred

Observed and predicted values from presence points and a raster map.

quantReclass

Reclassify continuous values based on quantiles

range01

Shrink or stretch a vector to make it range between 0 and 1

RMSE

Root mean square error

RsqGLM

R-squared measures for GLMs

similarity

Similarity measures

standard01

Standardize to 0-1 (or vice-versa)

threshMeasures

Threshold-based measures of model evaluation

varImp

Variable importance.

varPart

Variation partitioning

Analyses species distribution models and evaluates their performance. It includes functions for variation partitioning, extracting variable importance, computing several metrics of model discrimination and calibration performance, optimizing prediction thresholds based on a number of criteria, performing multivariate environmental similarity surface (MESS) analysis, and displaying various analytical plots. Initially described in Barbosa et al. (2013) <doi:10.1111/ddi.12100>.

  • Maintainer: A. Marcia Barbosa
  • License: GPL-3
  • Last published: 2026-01-09