统计研究 ›› 2008, Vol. 25 ›› Issue (6): 102-104.

• 论文 • 上一篇    

异方差模型参数估计的有效性研究

叶宗裕   

  1. 浙江师范大学工商管理学院
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-06-15 发布日期:2008-06-15

Research on the Efficiency of Parameter Estimator in Heteroscedastic Model

Ye Zongyu   

  • Received:1900-01-01 Revised:1900-01-01 Online:2008-06-15 Published:2008-06-15

摘要: 本文运用随机模拟方法,对误差序列异方差模型中加权最小二乘(GLS)估计的有效性进行研究。研究表明,GLS估计的有效性与异方差强度有关,当异方差强度较强时,GLS估计比普通最小二乘(OLS)估计有效;当异方差强度较弱时,GLS估计不如OLS估计有效。

关键词: 参数估计, 有效性, 异方差, 强度

Abstract: This paper studies the efficiency of GLS estimator in heteroscedastic model using the random simulation method. The results show that when the heteroscedastic intensity is high, the GLS estimators are more effective than OLS estimators, and when the heteroscedastic intensity is low, the GLS estimators are not more effective than OLS estimators.


 

Key words: Parameter Estimator, Efficiency, Heteroscedasticity, Intensity