纵向数据混合效应模型的Bayes局部影响

Bayesian Local Influence of Mixed-Effects Model for Longitudinal Data

基于分层先验思想,研究了适应于纵向数据的混合效应模型的Bayes局部影响,并根据纵向数据既包含个体又包含个体不同状态的特点,提出了两种便于合理分析数据的扰动方案,导出模型在上述各种扰动下效应参数的Bayes局部影响度量,最后给出实例。

Based on the hierarchical prior method, we study the Bayesian local influence of the mixed- effects model for longitudinal data. Two types of perturbation schemes are proposed based on the characteristics of longitudinal data which include both individuals and individual cases. The Bayesian local influential method and formulas of parameter estimates are provided under these perturbation schemes. An example is given for illustration.