华东师范大学学报(自然科学版) ›› 2004, Vol. 2004 ›› Issue (4): 24-27.

• 数学 统计学 • 上一篇    下一篇

单指标时间序列模型参数估计

张日权1,2   

  1. 1.华东师范大学统计系，上海200062; 2.雁北师范学院数学系，山西大同037000
  • 收稿日期:2003-03-12 修回日期:2003-05-09 出版日期:2004-12-25 发布日期:2004-12-25
  • 通讯作者: 张日权

Estimators of Parameters in A Single Index Time Series Model

ZHANG Ri-quan1,2   

  1. 1. Department of Statistics, East China Normal University, Shanghai 200062, China; 2. Department of Mathematics, Yanbei Normal Colloge，ShanxiDatong 037000,China
  • Received:2003-03-12 Revised:2003-05-09 Online:2004-12-25 Published:2004-12-25
  • Contact: ZHANG Ri-quan

摘要： 讨论了时间序列模型E(Y︱X)=G(θTX)的参数估计.采用核估计方法和平均导数法，在数据为户混合相依的情况下证明了该估计的渐近正态性.

关键词: 单指标模型, 核估计, 平均导数法, β-混合相依, 渐近正态性, 单指标模型, 核估计, 平均导数法, β-混合相依, 渐近正态性

Abstract:

This paper gives a solution to the problem of estimating coeffcients of index model in a time series. The kernel estimate method and the average derivative method are employed. Under the data being β-mixing depentent,the asymptotic normality of the estimator are established.

Key words: kernel estimate, averge derivative, β-mixing dependent, asymptotic normality, single index model, kernel estimate, averge derivative, β-mixing dependent, asymptotic normality

中图分类号: