Estimation and model selection in a class of semiparametric models for cluster data

Abstract

Stimulated by a study in Bangladesh about the first birth interval, we propose a semivarying-coefficient model for cluster data analysis. We consider the estimation procedure for the proposed model and establish the asymptotic results of the proposed estimators. Furthermore, we employ the cross-validation (CV) to identify the constant coefficients. The associated asymptotic properties are rigorously examined. Simulation studies are conducted to investigate the performance of the proposed estimation and the CV-based model selection procedure for finite sample size. Finally, our methods are used to analyse the aforementioned data set to explore how several factors affect the first birth interval in Bangladesh.