强混合样本下部分线性模型的经验似然推断（英文）  

Empirical Likelihood for Partially Linear Models Under Strong Mixing Samples

作　　者：黄玉[1] 秦永松 HUANG Yu;QIN Yongsong(i.Nanning University,Nanning 530200,Chin;Guangxi Normal University,Guilin 5~100~,China)

机构地区：[1]南宁学院公共教学部,广西南宁530200 [2]广西师范大学数学与统计学院,广西桂林541004

出　　处：《应用数学》2018年第4期873-883,共11页Mathematica Applicata

基　　金：Supported by the National Natural Science Foundation of Guangxi(2016GXNS FAA3800163);the Basic Ability Promotion Project for Young and Middle-age Teachers of Guangxi(KY2016YB862);the Professor Nurturing Engineering Project of Nanning University(2016JSGC09)

摘　　要：本文研究强混合样本下部分线性模型的经验似然推断,将分块技术应用到经验似然方法中,证明部分线性模型的参数β的对数经验似然比统计量的渐近分布为卡方分布,由此构造强混合样本下β的经验似然置信区间.在有限样本情况下给出数值模拟结果.In this paper, we study the blockwise empirical likelihood（EL） method to construct the confidence regions for the regression vector β in a partially linear model under strong mixing samples. It is shown that the blockwise EL ratio statistic for β is asymptotically χ-2 distributed, which are used to construct the EL-based confidence region for β under strong mixing samples. Results of a simulation study on the finite sample performance of the confidence region are reported.

关 键 词：强混合 部分线性模型 分块经验似然 置信区间 

分 类 号：O212.7[理学—概率论与数理统计]