Activity Number:
|
582
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 3, 2016 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Quality and Productivity Section
|
Abstract #318355
|
|
Title:
|
Efficient Follow-Up Strategies Using Foldovers with Column Permutations
|
Author(s):
|
William Li* and Dennis K. J. Lin
|
Companies:
|
University of Minnesota and Penn State University
|
Keywords:
|
De-alising ;
Factorial design ;
Foldover designs ;
Follow up strategy
|
Abstract:
|
Two-level fractional factorial designs are among the most commonly used experimental designs. The trade-off of the run size economy of using such designs is that many effects can be aliased. We discuss efficient follow-up strategies that involve using foldovers. Compared to existing approaches, the proposed method allows permutations of columns of the design. While augmenting a design by a foldover with column permutations may result in a nonregular combined design, the resulting design is usually able to de-alias a larger number of aliased two-factor interactions than existing foldovers. Several classes of commonly used designs including both regular and non-regular designs are studied. We demonstrate that most of the proposed designs are better than existing foldovers with respect to the minimum aberration criterion.
|
Authors who are presenting talks have a * after their name.