Sphere packing design for experiments with mixtures

Zikang Xiong, Liwei Liu, Jianhui Ning and Hong Qin

Statistics & Probability Letters, 2020, vol. 164, issue C

Abstract: Rotated sphere packing design is constructed by scaling, rotating and translating the lattice that has asymptotically lowest fill distance, its space-filling properties are very well. Currently, it can only be used for experimental design in hypercube. In this paper, we generalize the sphere packing design to simplex, which is the domain of experimental design with mixtures. In order to use the lattice method in simplex, a distance preserving transformation function is implemented to transform the simplex into the hyperplane, and then the iteration of rotating, scaling and disturbing is used to extract n lattice points as the design array. Some numerical comparisons between our method and several other popular methods are also provided. The results show that the designs generated by our algorithm are excellent according to the maximin distance criterion and its predictive ability is well. An additional searching method is also suggested to further improve the design.

Keywords: Experimental design with mixtures; Sphere packing design; Space-filling design; Lattice (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167715220301103
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:164:y:2020:i:c:s0167715220301103

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.spl.2020.108807

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().