Empirical Likelihood for Single-Index Regression Models under Negatively Associated Errors

被引:2
|
作者
Lin, Zheng-Yan [1 ]
Wang, Ran [1 ]
机构
[1] Zhejiang Univ, Dept Stat, Hangzhou 310027, Zhejiang, Peoples R China
基金
中国国家自然科学基金;
关键词
Blockwise; Empirical likelihood; NA errors; Negatively associated; Single-index model; RANDOM-VARIABLES; CONFIDENCE-REGIONS;
D O I
10.1080/03610926.2012.758746
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article, we use bockwise empirical likelihood technique to construct confidence regions for the parameter of the single-index models under negatively associated errors. It is shown that the blockwise empirical likelihood ratio statistic for the parameter of interest is asymptotically chi(2)-type distributed. The result can be used to obtain confidence regions for the parameter of interest.
引用
收藏
页码:1854 / 1868
页数:15
相关论文
共 50 条