Back To Index Previous Article Next Article Full Text

Statistica Sinica 26 (2016), 589-603 doi:http://dx.doi.org/10.5705/ss.2013.352

CONSTRUCTION OF SLICED MAXIMIN-ORTHOGONAL
LATIN HYPERCUBE DESIGNS
Jinyu Yang1, Hao Chen2, Dennis K. J. Lin3 and Min-Qian Liu1
1Nankai University, 2Tianjin University of Finance and Economics
and 3The Pennsylvania State University

Abstract: A sliced Latin hypercube design is a special Latin hypercube design that can be divided into slices of smaller Latin hypercube designs. This type of designs is useful for computer experiments with qualitative and quantitative factors, multiple experiments, data pooling, and cross-validation. Orthogonality and uniformity are important properties for Latin hypercube designs. In this paper, sliced maximin-orthogonal Latin hypercube designs are constructed using orthogonal designs, Goethals-Seidel arrays, and Kharaghani arrays. The resulting designs have both second-order orthogonality and good uniformity.

Key words and phrases: Computer experiment, maximin distance, orthogonality, sliced Latin hypercube design.

Back To Index Previous Article Next Article Full Text