Space-filling foldover designs for order-of-addition experiments under Kendall tau distance criteria

2026-05-26

AI Summary

This study addresses the challenge of experimentally investigating how the order of component addition affects system response, a problem for which full permutation designs are infeasible due to factorial growth. To overcome this, the authors construct space-filling fractional factorial designs based on the Kendall tau distance, establishing a theoretical link between this distance criterion and statistical optimality. They propose an efficient construction method that integrates foldover strategies with incremental updates and develop a foldover simulated annealing algorithm (FSA-KD) leveraging swap operations in permutation space. The resulting designs exhibit large minimum Kendall tau distances and stable distance distributions, demonstrating superior performance in surrogate modeling and permutation-based optimization tasks.

Abstract

Order-of-addition experiments arise when the response depends on the order in which a set of components is added. Since the number of possible orders increases factorially with the number of components, full permutation designs are rarely feasible except for small problems. This paper studies space-filling fractional designs for order-of-addition experiments based on the Kendall tau distance, a natural metric for comparing permutations through pairwise ordering disagreements. We consider the maximin Kendall tau distance criterion and related dispersion criteria, and establish their connections with statistical optimality under the pairwise ordering model and a Gaussian process model with the Mallows kernel. To construct such designs, we propose an efficient foldover simulated annealing algorithm, denoted by FSA-KD, based on swap moves in the permutation space, together with foldover and incremental updating strategies. Numerical studies show that the resulting FSA-KD designs have large minimum pairwise Kendall tau distances, denoted by k_min(D), and stable pairwise distance distributions, and perform well in surrogate modeling and permutation-based optimization tasks.

Problem

• order-of-addition experiments
• space-filling designs
• Kendall tau distance
• fractional factorial designs
• permutation space

Innovation

• Kendall tau distance
• space-filling design
• foldover simulated annealing
• order-of-addition experiment
• Mallows kernel