二值纵向数据的经验似然分析  

Analysis of binary longitudinal data with empirical likelihood method

作　　者：尹长明[1] 靳永涛 王亚东 YIN Chang-ming;JIN Yong-tao;WANG Ya-dong(College of Mathematics and Information Science,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学数学与信息科学学院,广西南宁530004

出　　处：《广西大学学报（自然科学版）》2020年第3期686-691,共6页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(11061002,11561010);广西自然科学基金资助项目(2015GXNSFAA139006)。

摘　　要：二值纵向数据在许多学科都有重要应用,特别是在生物、医学、经济和社会科学中。为使经验似然方法在分析二值纵向数据时更能满足现实复杂数据的各类约束以及在实际分析数据时更具有理论依据,在易验证和比较弱的条件下,给出较易验证的引理,进而证明二值纵向数据经验似然估计的相合性和渐近正态性,得到了其经验似然比检验的渐近分布,改进了文献中的相关结果。同时进行统计模拟表明经验似然方法分析二值数据时参数拟合度更好。Binary longitudinal data exerts an important role in application of many scientific subjects,especially in biology,medicine,economic and social sciences.The consistency and asymptotic normality of empirical likelihood estimation are proved under easier being testified lemmas and weaker assumptions,in order that all kinds of constraints of practical complex data are easier to be satisfied and that the method is more theoretically reliable in real longitudinal data analysis.The results demonstrate that the asymptotic distributions of empirical likelihood ratio test are obtained,and therefore the related result in the literature are improved.Meanwhile,the statistical simulation shows that the parameter fitness of empirical likelihood estimation is more accurate.

关 键 词：经验似然 纵向数据 LOGIT模型 参数估计 相合性 渐近分布 

分 类 号：O212.1[理学—概率论与数理统计]