Quantifying Performance of a Binary Classifier Through Weight of Evidence

The distributions of the weight of evidence (log Bayes factor) favouring case over noncase status in a test dataset (or test folds generated by cross-validation) can be used to quantify the performance of a diagnostic test (McKeigue (2018), ). The package can be used with any test dataset on which you have observed case-control status and have computed prior and posterior probabilities of case status using a model learned on a training dataset. To quantify how the predictor will behave as a risk stratifier, the quantiles of the distributions of weight of evidence in cases and controls can be calculated and plotted.


News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("wevid")

0.5.1 by Marco Colombo, 2 months ago


http://www.homepages.ed.ac.uk/pmckeigu/preprints/classify/wevidtutorial.html


Browse source code at https://github.com/cran/wevid


Authors: Paul McKeigue [aut] , Marco Colombo [ctb, cre]


Documentation:   PDF Manual  


GPL-3 license


Imports ggplot2, pROC, reshape2, zoo


See at CRAN