Work

SIS: An R Package for Sure Independence Screening in Ultrahigh-Dimensional Statistical Models

Year: 2018

Type: article

Abstract: We revisit sure independence screening procedures for variable selection in generalized linear models and the Cox proportional hazards model. Through the publicly available R package SIS, we provide a unified environment to carry out variable selection using iterative sure independence screening (ISIS) and all of its variants. For the regularization steps in the ISIS recruiting process, available penalties include the LASSO, SCAD, and MCP while the implemented variants for the screening steps are sample splitting, data-driven thresholding, and combinations thereof. Performance of these feature selection techniques is investigated by means of real and simulated data sets, where we find considerable improvements in terms of model selection and computational time between our algorithms and traditional penalized pseudo-likelihood methods applied directly to the full set of covariates.

Source: Journal of Statistical Software

DOI: 10.18637/jss.v083.i02

Authors: Diego Franco Saldana, Yang Feng

Institution: Columbia University

Language: English

Topic: Statistical Methods and Inference

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: diamond

Funder: National Science Foundation

Awards: G6671297155, CAREER: Statistical inference of network and relational data, Nonparametric classification, tuning parameter selection, and asymptotic stability for high-dimensional data