纵向数据半参数混合效应的Logistic模型  

Logistic model of semiparametric mixed effects for longitudinal data

作　　者：吴楠楠[1] 袁永生[1] 赵佩佩[1] 

机构地区：[1]河海大学理学院,江苏南京211100

出　　处：《云南民族大学学报（自然科学版）》2016年第3期234-239,共6页Journal of Yunnan Minzu University:Natural Sciences Edition

基　　金：江苏省水利科技创新基金(2011059);河海大学自然科学基金(2009426311)

摘　　要：为了深入探究Logistic模型的统计推断问题,联合半参数混合效应模型和Logistic模型建立了纵向数据半参数混合效应的Logistic模型,进一步求出该模型的极大似然函数、Fisher信息阵,利用QLB(quadratic lower-bound)算法求解参数的极大似然估计.最后进行数值模拟,结果表明在此模型的求解问题上QLB算法是Newton-Raphson算法的合理替代.In order to semiparametric mixed for longitudinal data, further explore the statistical inference problem of the logistic model, this paper combines the effect model and the logistic model to build a logistic model of semiparametric mixed effects figures out the maximum likelihood function of the model and the Fisher information matrix, and uses the QLB （ Quadratic Lower Bound） algorithm to solve the maximum likelihood estimation of the parame- ters. Finally, the results of the numerical simulation show that the QLB algorithm is a reasonable ahemative to the Newton -Raphson algorithm for such solutions.

关 键 词：纵向数据 混合效应 LOGISTIC模型 半参数 

分 类 号：O212[理学—概率论与数理统计]