Document Type

Journal Article

Department/Unit

Department of Mathematics

Language

English

Abstract

Uniform designs (UDs) have been widely used in various fields. Traditionally they were generated by so-called good lattice point (glp) sets. In this paper, we propose a new approach based on cyclic Latin squares (CLS). The UDs generated have much smaller discrepancies than those proposed by Wang and Fang (1981). A threshold accepting algorithm is employed for finding the CLS with smallest L2-discrepancy.

Keywords

Experimental design, Latin squares, L2-discrepancy, threshold accepting algorithm, uniform design, uniformity

Publication Date

1999

Source Publication Title

Statistica Sinica

Volume

9

Issue

3

Start Page

905

End Page

912

Publisher

Academia Sinica, Institute of Statistical Science

Peer Reviewed

1

ISSN (print)

19968507

Included in

Mathematics Commons

Share

COinS