摘要
研究了以NSD序列(negatively superadditive dependent)为误差的广义线性模型,得到了未知参数的M估计.在较弱的条件下,利用指数不等式、NSD序列加权和的强收敛性和Borel-Cantelli引理等证明了未知参数M估计的强相合性.此结果推广了独立误差和NSD误差的线性模型的相应结果.
In this paper, the generalized linear model of NSD sequence（negatively superadditive dependent） errors is studied and M estimator is obtained. Under weak conditions,the results are proved by using exponential inequalities and properties of NSD sequences. In addition, the results extend the corresponding results of the linear model with independent errors.
作者
蔡婷
胡宏昌
CAI Ting HU Hong-chang(School of Mathematics and Statistics, Hubei Normal University, Huangshi 435000, Chin)
出处
《数学的实践与认识》
北大核心
2017年第19期272-278,共7页
Mathematics in Practice and Theory
基金
国家自然科学基金(11471105)
湖北师范大学科研团队(T201505)
关键词
NSD序列
广义线性模型
M估计
强相合性
negatively superadditive dependent random variable
generalized linear models
M-estimates
convergence
