Weight of Evidence for Quantifying Performance of a Binary Classifier

[Up] [Top]

Documentation for package ‘wevid’ version 0.7.0

Help Pages

wevid-package Quantifying performance of a diagnostic test using the sampling distribution of the weight of evidence favouring case over noncase status
auroc.model Compute area under the ROC curve according to model-based densities
cleveland Example dataset based on cross-validated prediction of outcome in the Cleveland Heart Study
lambda.model Compute the expected information for discrimination (expected weight of evidence) from the model-based densities
means.densities Means of densities in cases and controls
plotcumfreqs Plot the cumulative frequency distributions in cases and in controls
plotroc Plot crude and model-based ROC curves
plotW plot log case/control density ratio against weight of evidence as a check that the densities are mathematically consistent
plotWdists Plot the distribution of the weight of evidence in cases and in controls
prop.belowthreshold Proportions of cases and controls below a given threshold of W (natural logs)
Wdensities.fromraw Adjust the crude densities of weights of evidence in cases and controls to make them mathematically consistent
Wdensities.mix Compute smoothed densities for a spike-slab mixture distribution
Wdensities.unadjusted Calculate the unadjusted smoothed densities of W in cases and in controls
weightsofevidence Calculate weights of evidence in natural log units
wevid Quantifying performance of a diagnostic test using the sampling distribution of the weight of evidence favouring case over noncase status
wtrue.results Summary evaluation of predictive performance