增长曲线模型中线性预测的泛容许性  

General Admissibility of Linear Predictor in Growth Curve Model

作　　者：周志龙[1] 朱宁[1] 方爱秋[1] 

机构地区：[1]桂林电子科技大学数学与计算科学学院,广西桂林541004

出　　处：《汕头大学学报（自然科学版）》2008年第4期8-15,共8页Journal of Shantou University：Natural Science Edition

摘　　要：在二次损失情况下,研究一般增长曲线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,得到了齐次线性预测和非齐次线性预测在对应的线性预测类中是泛容许预测时的充分必要条件.General admissibility of linear predictor of future observations in growth curve model under quadratic loss function is investigated.According to the definition for general admissible predictor of a linear predictable variable, the necessary and sufficient conditions for a linear predictable variable to be general admissible in the class of homogeneous linear predictor and the class of inhomogeneous linear predictors are established respectively.

关 键 词：泛容许性 线性预测 增长曲线模型 损失函数 

分 类 号：O212.1[理学—概率论与数理统计]