约束条件下多元随机效应模型中线性预测的泛容许性  

General admissibility of linear predictor in multivariate random effects model under restricted conditions

作　　者：周志龙[1] 陈小海[1] 

机构地区：[1]桂林电子科技大学职业技术学院,广西北海536000

出　　处：《大众科技》2012年第4期14-17,共4页Popular Science & Technology

基　　金：桂林电子科技大学职业技术学院院内教改项目资金资助

摘　　要：在约束条件下研究了多元随机效应模型中未来观察值线性预测的泛容许性。根据线性可预测变量泛容许预测的定义和Φ函数的合理条件,得到了齐次和非齐次线性预测在对应的线性预测类中是泛容许预测的充要条件。This article considers the general admissibility of linear predictor of future observations in the multivariate effects random effects model under restricted conditions.According to the definition for general admissible predictor of a linear predictable variable and the reasonable conditions of Φ function,the necessary and sufficient conditions for a linear predictable variable to be general admissible in classes of the homogeneous and inhomogeneous linear predictors are obtained,respectively.

关 键 词：泛容许性 线性预测 多元随机效应 损失函数 

分 类 号：O212.1[理学—概率论与数理统计]