平衡设计多向分类多元重复测量模型的Wilks检验  

Wilks Test Rule of Multivariate Repeated Survey Model in Equilibrium Design and Multiple-Way Classification

作　　者：张新育[1] 

机构地区：[1]郑州大学系统科学与数学系,郑州450001

出　　处：《应用概率统计》2010年第3期287-298,共12页Chinese Journal of Applied Probability and Statistics

基　　金：国家自然科学基金项目(10671183)资助

摘　　要：对平衡设计多向分类多元重复测量模型,利用极大似然比方法,推导了对各单个固定效应分别进行检验的Wilks型检验规则.并推导了对多个固定效应进行同时检验的检验规则.推导了非中心分布的参数与原始参数和样本容量的关系.By use of maximum likelihood ratio means, we present in this paper a Wilks test rule of each fixed effects in the equilibrium design and multiple-way classification model with repeated survey; then deduce a means to test each fixed effects simultaneously. At last, we deduce the function relation between non- central parameter and original parameter to reflected efficiency of this test rule.

关 键 词：多元重复测量模型 多向分类 平衡设计 极大似然比检验. 

分 类 号：O212[理学—概率论与数理统计]