摘要
m-END随机变量是一类很弱的负相依随机变量,它包含了NA随机变量、NOD随机变量和END随机变量。本文基于误差为m-END序列,研究非参数回归模型未知参数的加权估计,获得了加权估计的收敛性,包括矩相合性收敛速度和完全相合性收敛速度。作为应用,给出非参数回归模型未知参数近邻权估计的矩相合性收敛速度和完全相合性收敛速度。
m-END random variables are weakly dependent random variables, which contain NA random variables, NOD random variables and END random variables. In this paper, we investigate the weighted estimator of nonparametric regression model based on m-END errors. Some results of consistency such as mean convergence rate and complete convergence rate are obtained. As an application, the nearest neighbor weight estimator of nonparametric regression model is studied and mean convergence rate and complete convergence rate are presented.
作者
鲁俊
肖潇
陶浩然
乔旭东
吴秋月
杨文志
LU Jun XIAO Xia TAO Hao-ran QIAO Xu-dong WU Qiu-yue YANG Wen-zhi(a. Wendian Colleg b. School of Mathematical Sciences, Anhui University, Hefei Anhui 230039, China)
出处
《阜阳师范学院学报（自然科学版）》
2017年第3期30-34,共5页
Journal of Fuyang Normal University(Natural Science)
基金
国家自然科学基金(11501005
11671012)
安徽省自然科学基金(1508085J06)资助
关键词
回归模型
END随机变量
矩相合性
完全相合性
regression model
END random variables
mean consistency
complete consistency
