Data Mining for Longitudinal Data under Multicollinearity and Time Dependence using Penalized Generalized Estimating Equations

TL;DR

This paper introduces penalized generalized estimating equations with Elastic Net and L2-SCAD penalties to effectively select important variables and estimate effects in longitudinal Gaussian data with multicollinearity and time dependence.

Contribution

It proposes a novel method combining penalized GEE with Elastic Net and L2-SCAD penalties for variable selection in complex longitudinal data.

Findings

Method effectively handles multicollinearity and time dependence.

Consistent variable selection and effect estimation demonstrated.

Application to European life expectancy data illustrates practical utility.

Abstract

Penalized generalized estimating equations with Elastic Net or L2-Smoothly Clipped Absolute Deviation penalization are proposed to simultaneously select the most important variables and estimate their effects for longitudinal Gaussian data when multicollinearity is present. The method is able to consistently select and estimate the main effects even when strong correlations are present. In addition, the potential pitfall of time-dependent covariates is clarified. Both asymptotic theory and simulation results reveal the effectiveness of penalization as a data mining tool for longitudinal data, especially when a large number of variables is present. The method is illustrated by mining for the main determinants of life expectancy in Europe.