存在关联因子的裂区试验设计

Experimental design for split-plot with related factors

针对试验设计的关联因子中存在难以改变因子(HTC)的问题,提出了将嵌套效应建模引入裂区试验设计的处理方法,为存在关联因子的裂区试验设计问题提供了可行的解决方案.通过对裂区的设计,可以解决当因子水平的改变比较困难时,试验顺序不能随机化处理所带来的问题,而嵌套效应建模的引入使得试验设计的区域更符合实际需求,模型的解释也更合理.最后应用案例说明此方法可以更好地解决存在关联因子的裂区试验这类特殊的试验设计.

This paper concentrates on dealing with the existence of hard-to-change （HTC） factor among related factors in design of experiments （DOE）. Based on the discussion and comparative study of some approaches of experimental design with related factor, a viable solution is proposed for split-plot design containing related factors by combining split-plot design and nested effects modeling. By appealing to split-plot design, the problem that experimental order cannot be randomized with HTC factors is resolved. The application of nested effects modeling gives rise to more correspondence of the experimental region to industrial practice, and correspondingly more reasonable explanation of model. Finally, a real example application reveals that the proposed method can be successfully applied to resolve experimental design with HTC factors.