当前位置: 首页 > 首页 > 正文

明尼苏达大学卡尔森管理学院William Li教授:Optimal Foldovers of Orthogonal and Non-Orthogonal Designs

主题:Optimal Foldovers of Orthogonal and Non-Orthogonal Designs

主讲人:明尼苏达大学卡尔森管理学院William Li教授

主持人:统计学院林华珍教授

时 间:2018年8月28日(星期二)下午3:00-4:00

地 点:弘远楼408会议室

主办单位:统计研究中心 统计学院 科研处

 

主讲人简介:

- 明尼苏达大学卡尔森管理学院终身教授

(Professor in Supply Chain & Operation Dept., Carlson School of Management, U. of Minnesota)

- 冠名讲席教授(Chair Professor, Eric Jing Professor for Business Teaching and Research)

- 美国统计协会Fellow

- 清华大学本科,加拿大滑铁卢大学统计硕士,博士

- 复旦大学讲座教授

- 多次在中国,美国和欧洲的EMBA项目授课,以独特生动的教学方式广受学生欢迎并多次获奖

- 2次荣获卡尔森管理学院最佳教学奖(2006,2012)

- 连续两年(2015,2016)荣获明大和中大合办的EMBA最受欢迎老师奖

具体详情请见其个人主页:https://carlsonschool.umn.edu/faculty/william-li

 

摘要:

A commonly used follow-up experiment strategy involves the use of a foldover design by reversing the signs of one or more columns. In the first part of the talk we give a review of recent progress in obtaining optimal foldovers of orthogonal designs. In the second part, we develop a fast algorithm for constructing efficient two-level foldover designs that are not orthogonal. Recent work in two-level screening experiments has demonstrated the advantages of using small foldover designs, even when such designs are not orthogonal for the estimation of main effects (MEs). We provide further support for this argument. We show that these designs have equal or greater efficiency for estimating the ME model versus competitive designs in the literature and that our algorithmic approach allows the fast construction of designs with many more factors and/or runs. Our compromise algorithm allows the practitioner to choose among many designs making a trade-off between efficiency of the main effect estimates and correlation of the two-factor interactions (2FIs).