数学物理学报(英文版)

• 论文 • 上一篇    下一篇

VARIABLE SELECTION BY PSEUDO WAVELETS IN HETEROSCEDASTIC REGRESSION MODELS INVOLVING TIME SERIES

王清河; 周勇   

  1. 中国科学院数学与系统科学研究员院, 北京 100080
  • 收稿日期:2004-06-21 修回日期:2005-07-10 出版日期:2006-07-20 发布日期:2006-07-20
  • 通讯作者: 周勇
  • 基金资助:

    Zhou's research was partially supported by the foundations of National Natural Science (10471140) and (10571169) of China.

VARIABLE SELECTION BY PSEUDO WAVELETS IN HETEROSCEDASTIC REGRESSION MODELS INVOLVING TIME SERIES

Wang Qinghe; Zhou Yong   

  1. Institute of Applied Mathematics, Academy of Mathematics and Systems Science, The Chinese Academy of Sciences, Beijing 100080, China
  • Received:2004-06-21 Revised:2005-07-10 Online:2006-07-20 Published:2006-07-20
  • Contact: Zhou Yong

摘要:

A simple but efficient method has been proposed to select variables in
heteroscedastic regression models. It is shown that the pseudo empirical
wavelet coefficients corresponding to the significant explanatory variables
in the regression models are clearly larger than those nonsignificant ones,
on the basis of which a procedure is developed to select variables in regression models. The coefficients of the models are also estimated. All estimators are proved to be consistent.

关键词: Heteroscedastic regression models, variable selection, wavelets

Abstract:

A simple but efficient method has been proposed to select variables in
heteroscedastic regression models. It is shown that the pseudo empirical
wavelet coefficients corresponding to the significant explanatory variables
in the regression models are clearly larger than those nonsignificant ones,
on the basis of which a procedure is developed to select variables in regression models. The coefficients of the models are also estimated. All estimators are proved to be consistent.

Key words: Heteroscedastic regression models, variable selection, wavelets

中图分类号: 

  • 62G05