A Radial Scanning Statistic for Selecting Space-filling Designs in Computer Experiments
In the study of computer codes, filling space as uniformly as possible is important to describe the complexity of the investigated phenomenon. However, this property is not conserved by reducing the dimension. Some numeric experiment designs are conceived in this sense as Latin hypercubes or orthogonal arrays, but they consider only the projections onto the axes or the coordinate planes. We introduce a statistic which allows studying the good distribution of points according to all 1-dimensional projections. By angularly scanning the domain, we obtain a useful graphical representation. The advantages of this new tool are demonstrated on usual space-filling designs. Graphical, decisional and dimensionality issues are discussed.
KeywordsOrthogonal Array Computer Experiment Coordinate Plane Latin Hypercube Design Halton Sequence
Unable to display preview. Download preview PDF.
We wish to thank A. Antoniadis, the members of the DICE Consortium (http://www.dice-consortium.fr), the participants of ENBIS-DEINDE 2007, as well as two referees for their useful comments. We also thank Chris Yukna for his help in editing.
- Fisher, R. A. (1926). The arrangement of field experiments. Journal of the Ministry of Agriculture 33, 503–513.Google Scholar
- Knuth, D. (1997). The Art of Computer Programming, Volume 2: Seminumerical Algorithms, 3rd edition. Reading MA: Addison-Wesley.Google Scholar
- L’Ecuyer, P. and R. Simard (2007). Testu01: A C library for empirical testing of random number generators. ACM Transactions on Mathematical Software 33(4), Article 22.Google Scholar
- Loeppky, J., J. Sacks, and W. Welch (2008). Choosing the sample size of a computer experiment: A practical guide. Technical report, NISS.Google Scholar