有偏抽样下带信息观察和删失的面板数据的统计分析

面板数据经常出现在许多研究领域, 比如纵向跟踪研究. 在很多情况下, 纵向反应变量与观察 时间和删失时间都有关系. 本文在有偏抽样下, 针对这些相关性存在的情况, 利用一个不能观察的潜在 变量, 提出了一个联合建模方法来刻画纵向反应变量与观察时间和删失时间的相关性, 获得了模型中 回归参数的估计方程以及估计的渐近性质, 并通过数值模拟验证了这些估计在小样本下也是有效的, 同时把该估计方法用于一组实际的膀胱癌数据分析中.

Analysis of panel data with informative observation and censoring times under biased sampling

Panel data frequently occur in many studies such as longitudinal follow-up studies. In many situations, longitudinal responses may be correlated with observation times as well as censoring time. This paper considers the regression analysis of panel data where these correlations may exist under biased sampling, and a joint modeling approach that uses some latent variables to characterize the correlations is proposed. For inference about regression parameters, estimating equation approaches are developed and ...