Variable selection for semiparametric random-effects conditional density models with longitudinal data

Abstract

Variable selection using regularization approaches is an essential part of any statistical analysis and yet has been somewhat neglected for the semiparametric random-effects conditional density (RECD) models with longitudinal data. In this paper, we show how the regularization approach for variable selection can be adapted to the RECD models with longitudinal data. The computational and theoretical properties for variable selection consistency are established. Comprehensive simulation studies and a real data analysis further demonstrate the merits of our approach.