Iterative variable selection for high-dimensional data with binary outcomes

TL;DR

This paper introduces an iterative Bayesian variable selection method for high-dimensional binary outcome data, demonstrating competitive performance in identifying relevant variables while controlling false discoveries.

Contribution

The paper presents a novel structured screen-and-select Bayesian approach with non-local priors for high-dimensional binary data, implemented in an R package.

Findings

Competitive true positive rates compared to existing methods

Effective false discovery rate control

Applicable to high-dimensional binary outcome analysis

Abstract

We propose an iterative variable selection scheme for high-dimensional data with binary outcomes. The scheme adopts a structured screen-and-select framework and uses non-local prior-based Bayesian model selection within the same. The structured screening is based on the association of the independent variables with the outcome which is measured in terms of the maximum marginal likelihood estimator. Performance comparison with several well-known methods in terms of true positive rate and false discovery rate shows that our proposed method stands to be a competitive alternative for sparse high-dimensional variable selection with binary outcomes. The method has been implemented within the R package GWASinlps.