混料试验的R-最优设计  

R-Optimal Designs for Mixture Experiments

作　　者：赵洪雅[1] 关颖男[1] 韩大伟[1] 

机构地区：[1]东北大学理学院,辽宁沈阳110006

出　　处：《东北大学学报（自然科学版）》2000年第6期682-684,共3页Journal of Northeastern University(Natural Science)

基　　金：辽宁省科学技术基金资助项目! (972 2 0 0 )

摘　　要：介绍了依据参数联合估计的矩形置信区域而提出的一类新最优设计准则R -最优准则 ,并给出了其等价定理和设计不变性的性质·同时针对 ( q -1 )维单纯形上的二阶Scheff啨正则多项式模型 ,解决了其参数估计的RA new class of optimality criteria i.e. R optimality criterion is suggested,which depends on a joint confidence rectangle for the parameter estimation. And its equivalence theorem and invariance property which allows an easy calculation of optimal designs on many linearly transformed design spaces are given. For the full quadratic model widely used in the analysis of the experiments involving mixture is choosed as an example for the R optimal designs. It is proved that in the R optimal designs vertices and barycentres of depth 1 on the simplex S q-1 are support points.

关 键 词：混料设计 最优设计 R-最优性 参数联合估计 试验 

分 类 号：O212.6[理学—概率论与数理统计] TQ027[理学—数学]