含过程变量的K模型最优正交区组设计  

Optimal orthogonal block design for K model with process variables

作　　者：龚政 朱小渊 张崇岐 GONG Zheng;ZHU Xiao-yuan;ZHANG Chong-qi(School of Econ.and Statis.,Guangzhou Univ.,Guangzhou 510006,China)

机构地区：[1]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）》2021年第2期161-168,共8页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：国家自然科学基金(12071096)。

摘　　要：混料试验设计是研究混合物成份比例的试验设计,最优设计则是混料试验设计中重要的研究方向,其中以D-最优设计应用最为广泛.文中对K模型混料试验与最优准则进行介绍,对其含过程变量的3分量二阶K模型给出满足D-最优准则的正交区组设计,最后推广至q分量情形并证明.Mixture experimental design is the design which aims to study proportion of mixture components,the optimal design is an important research fields of mixture experiment design,D-optimal design is the most widely used among all optimal designs,this paper introduces the K model mixture experiments and the optimal criterion,after that,this paper puts forward the orthogonal block design of three-component second-order K model mixture ex periments which satisfying D-optimal criterion.At last,we generalize the work to q-component case.

关 键 词：混料试验 D-最优 正交区组设计 K模型 

分 类 号：O212.6[理学—概率论与数理统计]