Crandore Hub

wevid

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 (2019), <doi:10.1177/0962280218776989>). 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.

Versions across snapshots

VersionRepositoryFileSize
0.6.2 rolling linux/jammy R-4.5 wevid_0.6.2.tar.gz 72.9 KiB
0.6.2 rolling linux/noble R-4.5 wevid_0.6.2.tar.gz 72.7 KiB
0.6.2 rolling source/ R- wevid_0.6.2.tar.gz 25.2 KiB
0.6.2 latest linux/jammy R-4.5 wevid_0.6.2.tar.gz 72.9 KiB
0.6.2 latest linux/noble R-4.5 wevid_0.6.2.tar.gz 72.7 KiB
0.6.2 latest source/ R- wevid_0.6.2.tar.gz 25.2 KiB
0.6.2 2026-04-26 source/ R- wevid_0.6.2.tar.gz 25.2 KiB
0.6.2 2026-04-23 source/ R- wevid_0.6.2.tar.gz 25.2 KiB
0.6.2 2026-04-09 windows/windows R-4.5 wevid_0.6.2.zip 76.0 KiB
0.6.2 2025-04-20 source/ R- wevid_0.6.2.tar.gz 25.2 KiB

Dependencies (latest)

Imports

Suggests