emeryyi/hdtweedie: The Lasso for the Tweedie's Compound Poisson Model Using an IRLS-BMD Algorithm

This package implements a iteratively reweighed least square (IRLS) strategy that incorporates a blockwise majorization decent (BMD) method, for efficiently computing the solution paths of the (grouped) lasso and the (grouped) elastic net for the Tweedie model.

Getting started

Package details

AuthorWei Qian <weiqian@stat.umn.edu>, Yi Yang <yiyang@umn.edu>, Hui Zou <hzou@stat.umn.edu>
MaintainerWei Qian <weiqian@stat.umn.edu>
LicenseGPL-2
Version1.1
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("remotes")
remotes::install_github("emeryyi/hdtweedie")
emeryyi/hdtweedie documentation built on May 16, 2019, 5:06 a.m.