纵向数据混合效应模型的统计分析  

STATISTICAL ANALYSIS OF THE SEMIPARAMETRIC MIXED EFFECTS MODEL FOR LONGITUDINAL DATA

作　　者：钱伟民[1] 柴根象[1] 

机构地区：[1]同济大学应用数学系,上海200092

出　　处：《数学年刊（A辑）》2004年第4期445-456,共12页Chinese Annals of Mathematics

基　　金：国家自然科学基金(No.10171079)

摘　　要：本文研究了Tao等人在1999年提出的半参数混合效应模型,在不假设随机效应服从正态分布的条件下,用傅立叶变换的方法构造了随机效应的光滑非参数密度估计,给出了密度估计的公式,研究了其渐近性质,还构造了半参数混合效应模型中参数的估计方法并研究了其大样本性质。A semiparametric mixed effects regression model which was proposed by Tao et al. [17]is studied in different way contrast the predictive recursion method. The common assumption of Gaussian random effects is relaxed by using a Fourier method to provide a nonparametric smooth density estimate. As the formula for the density estimate is established, and its asymptotic properties is researched. The method for estimating the parameters of the semiparametric mixed effects model are also given. The large sample approximation of the density estimate and estimators of the parameters is studied.

关 键 词：混合效应模型 随机效应 傅立叶变换 渐近性质 

分 类 号：O212.1[理学—概率论与数理统计]