jlangaa/bouldr: A Psychology-Focused Tool for ROC Analyses

Extends the pROC package to do multiple nested Receiver Operator Characteristic (ROC) curve analyses, and graph them nicely with ggplot2. Many ROC packages focus on machine learning and classification use-cases. However, ROC is useful in psychology as well -- particularly in developing assessment instruments. A continuous score on a test can be ROC-ed against a target diagnosis to test the diagnostic efficiency of the test. ROC is the preferred approach because it assesses sensativity and specificity across the range of the scale, and can be used to identify optimal cut- scores. This package relies on pROC to perform the computation.

install.packages("remotes")
remotes::install_github("jlangaa/bouldr")