两水平部分因析设计的最小低阶效应混杂准则(英文)  

Minimum E-aberration Criterion for 2-level Fractional Factorial Designs

作　　者：赵胜利[1] 刘霞 

机构地区：[1]曲阜师范大学数学科学学院,曲阜市273165 [2]青岛市第49中学,山东省青岛市266043

出　　处：《曲阜师范大学学报（自然科学版）》2010年第4期1-8,共8页Journal of Qufu Normal University(Natural Science)

基　　金：supported by the NNSF of China(10826059,10901092);the NSF of Shandong Province of China (Q2007A05);the China Postdoctoral Science Foundation(20090451292)

摘　　要：根据效应分层原理,低阶效应比高阶效应更重要.在这种情况下,以别名集的结构为基础,提出了最小低阶效应混杂准则对2n-m设计进行排序.研究了新准则与其它最优性准则,即最大分辨度、最小低阶混杂、纯净效应和最大估计容量准则的联系.给出了具有16和32个水平组合的最小低阶效应混杂设计.The lower order effects are more important than the higher order effects according to the effect hierarchy principle.Under such circumstances,minimum E-aberration （MEA） criterion based on the structures of the alias sets is suggested to rank 2n-m designs.Relations between this new criterion and other optimality criteria,i.e.,the maximum resolution,minimum aberration,clear effects and maximum estimation capacity criteria,are studied.MEA designs with 16 and 32 runs are tabulated.

关 键 词：分辨度 最小低阶混杂 纯净 广义别名型 估计容量 

分 类 号：O212.6[理学—概率论与数理统计]