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.
作者
黄玉
秦永松
HUANG Yu;QIN Yongsong(i.Nanning University,Nanning 530200,Chin;Guangxi Normal University,Guilin 5~100~,China)
出处
《应用数学》
CSCD
北大核心
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)
关键词
强混合
部分线性模型
分块经验似然
置信区间
strong mixing
partially linear model
blockwise empirical likelihood
confidence region