Algorithms for Generating Maximin Latin Hypercube and Orthogonal Designs
Authors:
- 1 March 2011
- journal article
- research article
- Published by Springer Nature in Journal of Statistical Theory and Practice
- Vol. 5 (1) , 81-98
Abstract
Various proposals for implementing the maximin criterion for space-filling designs for use in computer experiments are reviewed. A new, well-performing algorithm is presented for the construction of maximin Latin hypercube designs using a 2-dimcnsional distance metric. An additional criterion, design orthogonality, is important when screening the effects of the input variables and a new search algorithm for orthogonal maximin designs is described for both 2-dimensional and multi-dimensional distance metrics. The new algorithms are shown to outperform existing algorithms under a variety of criteria.Keywords
This publication has 14 references indexed in Scilit:
- Construction of orthogonal Latin hypercube designsBiometrika, 2009
- Construction of orthogonal and nearly orthogonal Latin hypercubesBiometrika, 2009
- Efficient Nearly Orthogonal and Space-Filling Latin HypercubesTechnometrics, 2007
- A construction method for orthogonal Latin hypercube designsBiometrika, 2006
- Orthogonal Column Latin Hypercubes and Their Application in Computer ExperimentsJournal of the American Statistical Association, 1998
- Controlling Correlations in Latin Hypercube SamplesJournal of the American Statistical Association, 1994
- Orthogonal Array-Based Latin HypercubesJournal of the American Statistical Association, 1993
- Minimax and maximin distance designsJournal of Statistical Planning and Inference, 1990
- ACED: Algorithms for the Construction of Experimental DesignsThe American Statistician, 1985
- Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer CodeTechnometrics, 1979