强混合样本下非参数回归函数的经验似然推断  

Empirical Likelihood for Nonparametric Regression Functions under Strong Mixing Samples

作　　者：雷庆祝 秦永松 LEI Qingzhu;QIN Yongsong(College of Mathematics and Statistics,Guangxi Normal University,Guilin 541004,China)

机构地区：[1]广西师范大学数学与统计学院,桂林541004

出　　处：《应用数学学报》2019年第2期179-196,共18页Acta Mathematicae Applicatae Sinica

基　　金：国家自然科学基金(11671102;61662007);广西科学基金(2016GXNSFAA3800163;2017GXNSFAA198349)资助项目

摘　　要：在回归变量和响应变量的观察值为强混合随机变量序列时,本文利用分组经验似然方法构造了非参数回归函数的经验似然置信区间,同时通过模拟研究了本文提出的方法的优良性.A blockwise empirical likelihood approach is developed to construct confidence intervals for nonparametric regression functions when the observations of the response variable and the regressors form a strong mixing sample.The finite-sample performance of the method is evaluated through a simulation study.

关 键 词：Α-混合 非参数拟合 分组经验似然 置信区间 

分 类 号：O212.7[理学—概率论与数理统计]