QIU-Hongxiang-David/APACpredset: Asymptotically Probably Approximately Correct prediction sets

This package implements various methods to estimate APAC prediction sets under covariate shift. A scoring function should have been trained using data from the source population, while observations with missing dependent variable/outcome/label are available from the target population. When the outcome in the target population is observed or the likelihood ratio between target and source populations are known, PAC is achievable by other methods and methods in this package might be inferior.

Getting started

Package details

AuthorHongxiang Qiu
MaintainerHongxiang Qiu <david940408@gmail.com>
LicenseGPL-3
Version0.1.0
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("remotes")
remotes::install_github("QIU-Hongxiang-David/APACpredset")
QIU-Hongxiang-David/APACpredset documentation built on Aug. 11, 2022, 12:53 p.m.