Latin hypercube designs with controlled correlations and multi-dimensional stratification

Various methods have been proposed to construct Latin hypercube designs with small correlations. Orthogonal arrays have been used to construct Latin hypercube designs with multi-dimensional stratification. To integrate these two ideas, we propose a method to construct Latin hypercube designs with both controlled correlations and multi-dimensional stratification. For numerical integration, the constructed designs not only filter out lower-dimensional variance components as effectively as ordinary orthogonal array-based Latin hypercube designs, but also filter out bilinear terms more effectively. The proposed construction method entails no iterative searches. Sampling properties of the constructed designs are derived. Examples are given to illustrate the proposed construction method and the theoretical results.

[1]  Lih-Yuan Deng,et al.  Orthogonal Arrays: Theory and Applications , 1999, Technometrics.

[2]  Nam-Ky Nguyen.  A note on the construction of near-orthogonal arrays with mixed levels and economic run size , 1996 .

[3]  Randy R. Sitter,et al.  Orthogonal and nearly orthogonal designs for computer experiments , 2009 .

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

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

[6]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[7]  Boxin Tang.  Orthogonal Array-Based Latin Hypercubes , 1993 .

[8]  H. Niederreiter,et al.  Monte Carlo and Quasi-Monte Carlo Methods in Scientific Computing , 1995 .

[9]  R. Iman,et al.  A distribution-free approach to inducing rank correlation among input variables , 1982 .

[10]  H. D. Patterson.  The Errors of Lattice Sampling , 1954 .

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

[12]  A. Owen.  Lattice Sampling Revisited: Monte Carlo Variance of Means Over Randomized Orthogonal Arrays , 1994 .

[13]  A. Owen.  Randomly Permuted (t,m,s)-Nets and (t, s)-Sequences , 1995 .

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

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

[16]  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.

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

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

[19]  V. R. Joseph,et al.  ORTHOGONAL-MAXIMIN LATIN HYPERCUBE DESIGNS , 2008 .

[20]  Thomas Gerstner,et al.  Numerical integration using sparse grids , 2004, Numerical Algorithms.

[21]  Wei-Liem Loh.  On Latin hypercube sampling , 1996 .

[22]  J. C. Wang,et al.  Nearly orthogonal arrays with mixed levels and small runs , 1992 .

[23]  T. J. Mitchell,et al.  Exploratory designs for computational experiments , 1995 .