Open Access
December 2018 Optimal maximin $L_{1}$-distance Latin hypercube designs based on good lattice point designs
Lin Wang, Qian Xiao, Hongquan Xu
Ann. Statist. 46(6B): 3741-3766 (December 2018). DOI: 10.1214/17-AOS1674

Abstract

Maximin distance Latin hypercube designs are commonly used for computer experiments, but the construction of such designs is challenging. We construct a series of maximin Latin hypercube designs via Williams transformations of good lattice point designs. Some constructed designs are optimal under the maximin $L_{1}$-distance criterion, while others are asymptotically optimal. Moreover, these designs are also shown to have small pairwise correlations between columns.

Citation

Download Citation

Lin Wang. Qian Xiao. Hongquan Xu. "Optimal maximin $L_{1}$-distance Latin hypercube designs based on good lattice point designs." Ann. Statist. 46 (6B) 3741 - 3766, December 2018. https://doi.org/10.1214/17-AOS1674

Information

Received: 1 October 2017; Revised: 1 December 2017; Published: December 2018
First available in Project Euclid: 11 September 2018

zbMATH: 1411.62238
MathSciNet: MR3852667
Digital Object Identifier: 10.1214/17-AOS1674

Subjects:
Primary: 62K99

Keywords: computer experiment , Correlation , space-filling design , Williams transformation

Rights: Copyright © 2018 Institute of Mathematical Statistics

Vol.46 • No. 6B • December 2018
Back to Top