有偏抽样下带终止时间和带信息观察时间的纵向数据分析

Analysis of Longitudinal Data with Informative Observation and Terminal Event Times Under Biased Sampling

纵向数据经常出现在生物医学等实际领域,而且在许多情况下,观察时间和终止时间是带信息的,同时可能会存在有偏抽样.本文在有偏抽样下,对于带信息观察时间和终止时间的纵向数据,提出了一个联合建模方法,并利用借代力量方法给出了模型参数的估计,同时获得了这些估计的渐近性质.最后,提出一种模型检验方法.

Longitudinal data frequently occur in medical follow-up studies, and in many situations, there may exist informative observation times and a dependent terminal event time, as well as biased sampling. In this article, we propose joint modeling and analysis of longitudinal data with possibly informative observation times and a dependent terminal event time under biased sampling. A borrow-strength estimation procedure is developed for parameter estimation, and asymptotic properties of the proposed estimators are established. In addition, a model checking method is presented for assessing the adequacy of the model.