Panel数据模型中方差分量的精确检验  

Exact Tests of Variance Components in Panel Data Model

作　　者：程靖[1,2] 王松桂[3] 岳荣先[1] 

机构地区：[1]上海师范大学数理学院,上海200234 [2]巢湖学院数学系,安徽巢湖238000 [3]北京工业大学应用数理学院,北京100022

出　　处：《应用概率统计》2010年第1期89-98,共10页Chinese Journal of Applied Probability and Statistics

基　　金：国家自然科学基金项目(10671129);教育部高校博士点专项基金项目(20060270002)资助

摘　　要：本文利用广义p值和广义置信区间的概念构造含有三个随机效应的Panel数据模型中方差分量的几种新的精确检验和置信区间,并讨论它们在尺度变换下的不变性.通过模拟给出检验的功效和置信区间的覆盖率.模拟结果表明,广义p值理论方法应用于含有冗余参数的Panel数据模型参数检验问题是灵活而有效的.In this paper, some new exact tests and confidence intervals of variance components in Panel data model with three random effects are constructed base on the concepts of generalized p value and generalized confidence interval. Invariance of these tests and confidence intervals under scale transformation is also discussed in the paper.The powers of these tests and coverage probabilities are obtained by numerical simulations. It is shown that generalized p value method is feasible and effective to resolve the hypothesis testing problems with nuisance parameters.

关 键 词：Panel数据模型 随机效应 广义P值 广义置信区间 方差分量 

分 类 号：O212.1[理学—概率论与数理统计]