Sure screening for estimating equations in ultra-high dimensions

TL;DR

This paper introduces EEScreen, a versatile screening method for high-dimensional data using estimating equations, which unifies and generalizes existing model-based and model-free screening techniques, with demonstrated effectiveness.

Contribution

The paper proposes EEScreen and iEEScreen, novel model-free screening procedures applicable to any model fit with estimating equations, extending existing methods.

Findings

EEScreen performs well in simulations across different estimating equations.

iEEScreen is closely related to boosting methods for estimating equations.

Both methods are effective in real data application.

Abstract

As the number of possible predictors generated by high-throughput experiments continues to increase, methods are needed to quickly screen out unimportant covariates. Model-based screening methods have been proposed and theoretically justified, but only for a few specific models. Model-free screening methods have also recently been studied, but can have lower power to detect important covariates. In this paper we propose EEScreen, a screening procedure that can be used with any model that can be fit using estimating equations, and provide unified results on its finite-sample screening performance. EEScreen thus generalizes many recently proposed model-based and model-free screening procedures. We also propose iEEScreen, an iterative version of EEScreen, and show that it is closely related to a recently studied boosting method for estimating equations. We show via simulations for two different estimating equations that EEScreen and iEEScreen are useful and flexible screening procedures, and demonstrate our methods on data from a multiple myeloma study.