| VARIABLE SELECTION BY PSEUDO WAVELETS IN HETEROSCEDASTIC REGRESSION MODELS INVOLVING TIME SERIES |
| |
| 作者姓名： | 王清河 周勇 |
| |
| 作者单位： | Department of Applied Mathematics University of Petroleum Shandong 257062，China，Institute of Applied Mathematics Academy of Mathematics and Systems Science The Chinese Academy of Sciences，Beijing 100080，China |
| |
| 基金项目： | Zhou's research was partially supported by the foundations of NatioiMd Natural Science (10471140) and (10571169) of China. |
| |
| 摘 要： | A simple but efficient method has been proposed to select variables in het-eroscedastic 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： | 异方差衰退模型 变量选择 小波 相应系数 |
| 收稿时间： | 2004-06-21 |
| 修稿时间： | 2005-07-10 |
VARIABLE SELECTION BY PSEUDO WAVELETS IN HETEROSCEDASTIC REGRESSION MODELS INVOLVING TIME SERIES |
| |
| Wang Qinghe, Zhou Yong.VARIABLE SELECTION BY PSEUDO WAVELETS IN HETEROSCEDASTIC REGRESSION MODELS INVOLVING TIME SERIES[J].Acta Mathematica Scientia,2006,26(3):469-476. |
| |
| Authors: | Wang Qinghe Zhou Yong |
| |
| Abstract: | A simple but efficient method has been proposed to select variables in het-eroscedastic 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. |
| |
| Keywords: | Heteroscedastic regression models variable selection wavelets |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
