摘要
通过研究一阶半变系数混料回归模型,转变成混合效应混料回归模型,进而得到模型的信息矩阵。针对一阶半变系数混料回归模型,求出其单纯形-中心设计的D-最优设计和G-最优设计,由此得到一阶半变系数混料回归模型中D-最优设计与G-最优设计不等价。
By studying first-order mixture regression model with semi-varying coefficient, it is obtained the mix-effect mixture regression model by using the variant method and then obtained the information matrix. The D-optimum design and G-optimum design for first order mixture regression model with semi-varying coefficient are calculated. Meanwhile, it is showed that there are not equivalent between D-optimum design and G-optimum design.
作者
刘妙玲
张崇岐
LIU Miao-ling;ZHANG Chong-qi(School of Mathematic and Science Information,Guangzhou University,Guangdong Guangzhou 510006,China)
出处
《数理统计与管理》
CSSCI
北大核心
2018年第6期1041-1049,共9页
Journal of Applied Statistics and Management
基金
国家自然科学基金(11671104)
广州大学全日制研究生“基础创新”项目(2017GDJC-M31)
关键词
半变系数
混料回归模型
信息矩阵
最优设计
semi-varying coefficient
mixture regression model
information matrix
optimum design
