Optimal centroid-class designs for mixture order-of-addition experiments
This article addresses optimal designs for mixture order-of-addition (MOofA) experiments based on higher-order centroid polynomial models. We present relevant conclusions concerning the information matrix, D- and A-optimality criterion functions for MOofA centroid-class designs. Explicit expressions for D- and A-optimal designs under second-order MOofA centroid polynomial models are derived, along with proofs based on the equivalence theorem. For third- and higher-order centroid polynomial models, a stochastic search algorithm is proposed to construct MOofA centroid-class optimal designs. Numerical results demonstrate that the proposed algorithm effectively identifies MOofA optimal designs under higher-order centroid polynomial models.
Authors
- Junpeng Li (ORCID: https://orcid.org/0000-0003-4028-2703)
- Guanghui Li (ORCID: https://orcid.org/0009-0007-0120-1268)
- Xin Feng
Institutions
- Jishou University (CN)
- Kaili University (CN)
Publication Details
- Journal
- Communications in Statistics - Simulation and Computation
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1080/03610918.2026.2753593
- Primary Topic
- Optimal Experimental Design Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China