DudbridgeLab/multipred: Calculates measures of accuracy for risk predictors of multiple outcomes.

Accuracy can be evaluated in four senses: outcome-wise, joint, and panel-wise (weak sense and strong sense). For convenience the weak panel-wise sense is also called "screening", and the strong panel-wise sense simply "panel-wise". In each sense, accuracy can be measured empirically, within data sets given as input, or theoretically, given parameters of an underlying multivariate liability threshold model.

install.packages("remotes")
remotes::install_github("DudbridgeLab/multipred")