Skip to contents

SSCI: an R Package of the new sparsified simultaneous confidence intervals (SSCI) for high-dimensional linear models

Overview

This package implements a new notion called sparsified simultaneous confidence intervals (SSCI) for high-dimensional linear models, as presented in Zhu et al. (2024). This package can generate a group of intervals containing the true coefficient vector of a high-dimensional linear model simultaneously with a prespecified confidence level. The intervals are sparse in the sense that some of the intervals’ upper and lower bounds are shrunk to zero (i.e., [0,0]), indicating the unimportance of the corresponding covariates. These covariates should be excluded from the final model. The remaining intervals, either containing zero (e.g., [-1,1] or [0,1]) or not containing zero (e.g., [2,3]), indicate the plausible and significant covariates, respectively. This package also provides a visualization tool, the SSCI plot, which visualizes these intervals. The package can construct the SSCI based on different selection procedures.

Installation

The SSCI package will be available on SSCI CRAN soon.

# Install the development version from GitHub
if (!requireNamespace("devtools")) install.packages("devtools")
devtools::install_github("XiaoruiZhu/SSCI")

Install SSCI from the CRAN 

# Install from CRAN
install.packages("SSCI")