Empirical Likelihood for Varying Coefficient EV Models under Longitudinal Data

In this paper, a varying coefficient errors-in-variables model under longitudinal data is investigated. An empirical likelihood based bias-correction approach is proposed. It is proved that the proposed statistics are asymptotically chi-squared under some mild conditions, and hence can be used to construct the confidence regions of the parameters of interest. Finite sample performance of the proposed method is illustrated in a simulation study. The proposed methods are applied to an AIDS clinical trial dataset.