Efficient estimation of panel count data with dependent observation process

Abstract

In follow-up studies, panel count data are frequently encountered in which subjects are only observed under discrete time points rather than continuous time points. The observation process may be correlated with the panel count data. In this paper, a more general panel count data model with dependent observation process is proposed. A penalized composite quantile regression (CQR) is developed for the panel count data. Consistency and oracle properties are established under some mild regularity conditions. Some numerical simulations are carried out to confirm and assess the performance of the proposed model and approach, and an example from the blander cancer study is also provided.