三水平部分因析设计中条件主效应的变量选择  

Variable Selection of Conditional Main Effect in the three-Level Fractional Factorial Designs

作　　者：吴宇桐 蔡霞[1] 陈亚慧 WU Yu-tong;CAI Xia;CHEN Ya-hui(School of Science,Hebei University of Science and Technology,Shijiazhuang 050018,China)

机构地区：[1]河北科技大学理学院,河北石家庄050018

出　　处：《安徽师范大学学报(自然科学版)》2023年第6期511-515,519,共6页Journal of Anhui Normal University(Natural Science)

基　　金：国家自然科学基金项目(12001155);河北省自然科学基金项目(A2022208001).

摘　　要：显著效应识别是部分因析设计中一个非常重要的研究内容,但按照传统方法识别出的交互作用项往往很难解释。在传统分析方法的基础上,结合LASSO方法,本文提出一种在三水平部分因析设计中条件主效应的变量选择方法,并将其与传统方法做了分析比较。结果表明,基于LAS-SO回归的条件主效应分析方法得到的模型项数更少,p值更小,拟合程度更高,选取的条件主效应项更容易解释。Significant factor identification is a very important study in fractional factorial designs,but the interaction terms identified according to the traditional method are often difficult to interpret.Combined with the LASSO method,this paper proposes a variable selection method for conditional main effect in a three-level fractional factorial design.The results show that the conditional main effect analysis method based on LASSO regression yields fewer model terms,smaller p-values,better fit,and the selected conditional main effect terms are easier to explain.

关 键 词：试验设计 条件主效应 LASSO回归 变量选择 部分因析设计 

分 类 号：O212.6[理学—概率论与数理统计]