首页 | 本学科首页   官方微博 | 高级检索  
     检索      

线性模型中F-检验的稳健性
引用本文:邱红兵,罗季.线性模型中F-检验的稳健性[J].数学学报,2010,53(2):385-392.
作者姓名:邱红兵  罗季
作者单位:广东工业大学应用数学学院;浙江财经学院数学与统计学院;
基金项目:国家社会科学基金项目(07CTJ001); 广东工业大学校青年基金项目(082024); 浙江省教育厅科研项目(Y200802985); 浙江财经学院重大课题(2008YJZ06)
摘    要:本文讨论了一般线性模型中关于均值参数β的线性假设基于广义最小二乘估计的F-检验统计量的稳健性问题.主要研究了当误差的协方差矩阵含有参数时,设计阵可以列降秩情况下的F-检验统计量的稳健性,得到了F(V(θ))为该假设下F-检验统计量的误差协方差矩阵的最大类.并讨论了分块线性模型中,关于分块参数的线性假设的F-检验统计量的稳健性.

关 键 词:线性模型  稳健性  F-检验统计量
收稿时间:2009-02-09
修稿时间:2009-10-27

Robustness of F-test in Linear Models
Hong Bing QIU Faculty of Applied Mathematics,Guangdong University of Technology,Guangzhou ,P.R.China Ji LUO School of Mathematics , Statistics,Zhejiang University of Finance , Economics,Hangzhou ,P.R.China.Robustness of F-test in Linear Models[J].Acta Mathematica Sinica,2010,53(2):385-392.
Authors:Hong Bing QIU Faculty of Applied Mathematics  Guangdong University of Technology  Guangzhou  PRChina Ji LUO School of Mathematics  Statistics  Zhejiang University of Finance  Economics  Hangzhou  PRChina
Institution:Hong Bing QIU Faculty of Applied Mathematics,Guangdong University of Technology,Guangzhou 510006,P.R.China Ji LUO School of Mathematics , Statistics,Zhejiang University of Finance , Economics,Hangzhou 310018,P.R.China
Abstract:Robustness of F-test based on the general least squares estimate used in testing linear restrictions is discussed in general linear model. We mainly study robustness of the F-statistics in the cases of variance matrix of error including parameter and design matrix with reduced-rank columns. The maximal classes of variance matrix of error are derived, in which F(V(θ)) is F-statistics of the linear restriction. Also the robustness of F-statistics with respect to linear restrictions for partitioned parameters in partitioned linear model is considered.  
Keywords:linear model  robustness  F-statistics  
本文献已被 CNKI 等数据库收录!
点击此处可从《数学学报》浏览原始摘要信息
点击此处可从《数学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号