摘要
考虑线性回归模型y_i=x_i^Tβ_0+e_i,i=1,2,…,n,其中误差{e_i,i=1,2,...,n}为渐近几乎负相关的随机序列.研究了该模型中参数的M估计的强相合性,也得到了AANA序列的Bernstein型不等式,推广了NA样本的相应结论.
Consider the linear regression model y_i = x_i^Tβ_0 ＋ e_i,1 i n,where the errors{e_i} are asymptotically almost negatively associated random variables.The strong consistency of M-estimator of parameter is investigated,and Bernstein type inequality for AANA random variables is also obtained,which extend the corresponding results for negatively associated random variables.
出处
《数学进展》
CSCD
北大核心
2016年第3期463-470,共8页
Advances in Mathematics（China）
基金
国家自然科学基金(No.11471105)
关键词
渐近几乎负相关
线性回归模型
M估计
强相合性
BERNSTEIN型不等式
asymptotically almost negatively associated
linear regression models
Mestimation
strong consistency
Bernstein type inequality
