数学物理学报

• 论文 • 上一篇    下一篇

误差为鞅差序列的部分线性模型中估计的强相合性

李国亮; 刘禄勤   

  1. 武汉大学数学与统计学院 武汉 430072
  • 收稿日期:2005-09-28 修回日期:2006-06-23 出版日期:2007-10-25 发布日期:2007-10-25
  • 通讯作者: 李国亮
  • 基金资助:
    国家自然科学基金(10071058-2)资助

Strong Consistency of a Class of Estimators in Partial Linear

Model under Martingale Difference Sequence

Li Guoliang; Liu Luqin   

  1. School of Math and Statistics, Wuhan University, Wuhan 430072
  • Received:2005-09-28 Revised:2006-06-23 Online:2007-10-25 Published:2007-10-25
  • Contact: Li Guoliang

摘要: 考虑回归模型:yi=xi β +g(ti)+σiei ,i=1,2,...,n,其中 σi=f(ui), (xi,ti,ui)是固定非随机设计点列,f(.),\ g(.)$\ 是未知函数,β是待估参数,ei是随机误差且关于非降σ -代数列{Fi,i≥1} 为鞅差序列.对文献[1]给出的基于f(.)及g(.)的一类非参数估计的β的最小二乘估计βn和加权最小二乘估计βn,在适当条件下证明了它们的强相合性,推广了文献[6]在ei为iid情形下的结果.

关键词: 部分线性模型, 最小二乘估计, 加权最小二乘估计, 鞅差序列, 强相合性

Abstract:
Consider the heteroscedastic regression model: yi=xi β +g(ti)+σiei ,i=1,2,...,n,where Here σi=f(ui), (xi,ti,ui)Here the design points (xiti,ui) are known and nonrandom, g and f are unknown functions , and β is the parameter needed to be estimated,ei is the random error and a martingale difference sequence in relation to the undecreasing σ-algebra series {Fi,i≥1}. For the least squares estimator βn and the weighted least squares estimator βn of β given in [1] based on the family of nonparametric estimates of g(.) and f(.), the authors establish their strong consistency under suitable conditions, thereby improve the the result where ei is iid in [6].

Key words: Partial linear model, Least squares estimator, Weighted least squares
estimator,
Strong consistency, Martingale difference

中图分类号: 

  • 62G20