Controlling Correlations in Sliced Latin Hypercube Designs

A sliced Latin hypercube design is a special Latin hypercube design that can be partitioned into smaller Latin hypercube designs. We propose an algorithm to construct sliced Latin hypercube designs with controlled column-wise correlations for each slice and the entire design. The proposed algorithm can significantly decrease the column-wise correlations in each slice as the number of slices increases even if the number of runs in each slice is fixed. The algorithm is flexible in sample size and can be extended to control the quadratic canonical correlations of the larger design. The convergence behavior of the algorithm is studied and the effectiveness of the algorithm is illustrated by several examples.

[1]  Dennis K. J. Lin,et al.  Construction of sliced orthogonal Latin hypercube designs , 2013 .

[2]  Jennifer Werfel,et al.  Orthogonal Arrays Theory And Applications , 2016 .

[3]  Jian-Feng Yang,et al.  Construction of sliced (nearly) orthogonal Latin hypercube designs , 2014, J. Complex..

[4]  Ronald L. Iman.  Latin Hypercube Sampling , 2008 .

[5]  A. Owen.  Controlling correlations in latin hypercube samples , 1994 .

[6]  Min-Qian Liu,et al.  Resolvable orthogonal array-based uniform sliced Latin hypercube designs , 2014 .

[7]  Kenny Q. Ye.  Orthogonal Column Latin Hypercubes and Their Application in Computer Experiments , 1998 .

[8]  Boxin Tang,et al.  SELECTING LATIN HYPERCUBES USING CORRELATION CRITERIA , 1998 .

[9]  Dennis K. J. Lin,et al.  A construction method for orthogonal Latin hypercube designs , 2006 .

[10]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[11]  Peter Z. G. Qian.  Sliced Latin Hypercube Designs , 2012 .

[12]  Stephen J. Wright,et al.  Validating Sample Average Approximation Solutions with Negatively Dependent Batches , 2014, 1404.7208.

[13]  Peter Z. G. Qian,et al.  Making corrections to your proof , 2012 .

[14]  Peter Z. G. Qian,et al.  Maximin Sliced Latin Hypercube Designs with Application to Cross Validating Prediction Error , 2017 .

[15]  Dennis K. J. Lin,et al.  Construction of orthogonal Latin hypercube designs , 2009 .

[16]  M. E. Johnson,et al.  Minimax and maximin distance designs , 1990 .

[17]  T. J. Mitchell,et al.  Bayesian design and analysis of computer experiments: Use of derivatives in surface prediction , 1993 .

[18]  Dennis K. J. Lin,et al.  Sliced Latin hypercube designs via orthogonal arrays , 2014 .

[19]  William A. Brenneman,et al.  Optimal Sliced Latin Hypercube Designs , 2015, Technometrics.

[20]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .