具有指数相关的纵向数据模型中的齐性检验  

Testing for Homogeneity of Exponential Correlation Models Based on Longitudinal Data

作　　者：范俊花[1,2] 林金官[1] 

机构地区：[1]东南大学成贤学院,江苏南京210088 [2]东南大学数学系,江苏南京210096

出　　处：《山西师范大学学报（自然科学版）》2008年第4期1-5,共5页Journal of Shanxi Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助(10671032)

摘　　要：在纵向数据分析中,经常假定方差是齐性的,但是该假定未必正确.对具有AR(1)误差的非线性纵向数据模型,林金官和韦博成讨论了其方差和相关系数的齐性检验.本文针对具有指数相关协方差结构的纵向数据模型,研究了方差齐性和相关系数齐性的检验,得到了检验的score统计量,并对葡萄糖数据进行了分析.In longitudinal data analysis, homogeneity of variance is a basic assumption. However, this assumption is not necessarily appropriate. Lin and Wei considered the tests for homogeneity of within-individual variances and between-individual autocorrelation coefficients of nonlinear models with AR（ 1 ） errors based on longitudinal data. In this paper we discuss the tests for homogeneity of variances and correlation coefficients in longitudinal data model with exponential correlation covariance structure and obtain several score test statistics. The glucose data is used to illustrate our results.

关 键 词：纵向数据 指数相关模型 异方差 相关系数 SCORE检验 

分 类 号：O212.1[理学—概率论与数理统计]