J4

• 数学 • 上一篇    下一篇

线性模型中广义最小二乘估计关于误差分布的稳健性

邱红兵1, 罗 季2   

  1. 1. 广东工业大学 应用数学学院, 广州 510006; 2. 浙江财经学院 数学与统计学院, 杭州 310018
  • 收稿日期:2008-03-24 修回日期:1900-01-01 出版日期:2009-01-26 发布日期:2009-01-26
  • 通讯作者: 罗 季

On Robustness of GLSE in Terms of Error Distributionsin Linear Model

QIU Hongbing1, LUO Ji2   

  1. 1. Department of Applied Mathematics, Guangdong University of Technology, Guangzhou 510006, China;2. School of Mathematics and Statistics, Zhejiang University of Finance and Economics, Hangzhou 310018, China
  • Received:2008-03-24 Revised:1900-01-01 Online:2009-01-26 Published:2009-01-26
  • Contact: LUO Ji

摘要: 研究一般线性模型下广义最小二乘估计关于误差分布的稳健性, 给出了误差分布的最大分布类, 使得当误差向量的分布在此范围内变动时, 广义最小二乘估计在广义均方误差准则下为一致最优估计.

关键词: 线性模型, 广义均方误差, 稳健性, 广义最小二乘估计, 最佳线性无偏估计

Abstract: Robustness of generalized least square estimator in terms of error distributions in general linear model was discussed. We explored the maximal class of distributions of error term, in which the GLSE possesses robustness, that is, the GLSE is the best linear estimator under the criterion of minimizing the generalized MSE matrix with the error distribution varying within the maximal class.

Key words: linear model, generalized MSE, robust, generalized least square estimator, best linear unbiased estimator

中图分类号: 

  • O212.1