A Divide-and-Conquer Method for Sparse Risk Prediction and Evaluation

The package solid consists 1) a screening and one-step linearization infused DAC (SOLID) algorithm to fit sparse logistic regression to massive datasets, and 2) a modified cross-validation (MCV) that utilizes the side products of the SOLID hence substantially reduce the computational burden.

Details

Package:solid
Type:Package
Version:1.1
Date:2019-11-06
License: GPL>=2

Author

Chuan Hong
Yan Wang
Tianxi Cai
Maintainer: Chuan Hong <chuan_hong@hms.harvard.edu>