Metaheuristic Solutions to Order-of-Addition Design Problems

Zack Stokes, Weng Kee Wong, Hongquan Xu

研究成果: Article同行評審


There is increasing recognition that the order of administration of drugs in drug combination studies can markedly affect the outcome. Similarly, manufactured products are often sequentially produced and the final quality frequently depends on the order of assembly. Order-of-addition designs account for the order of administration of the components, and they are quite prevalent, yet research in this area is quite limited. Because of the large dimension of such optimization problems, analytical approaches are invariably very limited and apply to simple setups only. Numerical approaches are also seriously underdeveloped. To this end, we employ two exemplary nature-inspired metaheuristic algorithms, Differential Evolution (DE) and Particle Swarm Optimization (PSO), to search for efficient order-of-addition designs for two classes of important inferential problems: (a) estimating parameters in an imprecisely specified model, and (b) constructing space-filling designs without specifying a model. We evaluate the capability of DE and PSO to solve the two classes of order-of-addition design problems and compare their performance with other algorithms that have been used to tackle somewhat similar problems. Using different criteria, we demonstrate that DE and PSO clearly outperform current algorithms by a wide margin. Supplementary materials containing codes to generate all results in this article are available online.

All Science Journal Classification (ASJC) codes

  • 統計與概率
  • 離散數學和組合
  • 統計、概率和不確定性


深入研究「Metaheuristic Solutions to Order-of-Addition Design Problems」主題。共同形成了獨特的指紋。