混料分类模型的最优设计  

Optimal design of mixture classification model

作　　者：吴惠彬 李光辉 张崇岐 WU Huibin;LI Guanghui;ZHANG Chongqi(School of Mathematics and Information Sciences,Guangzhou University,Guangzhou 510006,China;School of Economics and Statistics,Guangzhou University,Guangzhou 510006,China)

机构地区：[1]广州大学数学与信息科学学院,广东广州510006 [2]广州大学经济与统计学院,广东广州510006

出　　处：《高校应用数学学报（A辑）》2018年第1期13-20,共8页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：国家自然科学基金(11671104)

摘　　要：由于混料试验中的响应变量常受到定性因子的影响,故通常采用分类模型来建模.通过已有的D-最优设计的结论导出A-,R-最优设计的方差函数以及等价条件,并给出实例分析.Response variables are often affected by qualitative factors.For this reason,classification models are used.The A-and R-optimal design for classication models has been existed according to the theory of D-optimal design for the model with qualitative factors.The variance function and equivalent conditions will be given under those situations.At last,examples are presented to illustrate and check this method in constructing optimal designs.

关 键 词：混料试验 最优设计 方差函数 

分 类 号：O212.6[理学—概率论与数理统计]