Nonparametric estimation of mean and covariance structures for longitudinal data

被引:5
|
作者
Lin, Huazhen [1 ]
Pan, Jianxin [2 ]
机构
[1] Southwestern Univ Finance & Econ, Sch Stat, Chengdu, Sichuan, Peoples R China
[2] Univ Manchester, Sch Math, Manchester M13 9PL, Lancs, England
基金
中国国家自然科学基金; 国家杰出青年科学基金;
关键词
Modified Cholesky decomposition; modified local linear smoothing method; non-parametric mean-covariance models; single index models; GENERALIZED ESTIMATING EQUATIONS; REGRESSION-ANALYSIS; MODELS;
D O I
10.1002/cjs.11189
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article we propose a novel nonparametric regression method to model the mean and covariance structures for longitudinal data. A modification of local linear smoothing estimation techniques is used to estimate the parameters and unknown functions in the model. Theoretical properties including uniform consistency and asymptotic normality are studied under certain mild conditions. Simulation studies are carried out to evaluate the efficacy of the proposed method, and real data analysis is provided for illustration. The Canadian Journal of Statistics 41: 557-574; 2013 (c) 2013 Statistical Society of Canada
引用
收藏
页码:557 / 574
页数:18
相关论文
共 50 条