© 2001 by Biometrika Trust
Optimal and orthogonal Latin hypercube designs for computer experiments
1 Department of Applied Statistics, University of Reading, Reading RG6 6FN, U.Kn.a.butler{at}reading.ac.uk
Latin hypercube designs are often used in computer experiments as they ensure that few design points are redundant when there is effect sparsity.In this paper, designs suitable for factor screening are presented and they are shown to be efficient in terms of runs required per factor as well as having optimal and orthogonal properties. Designs orthogonal under full second-order models are also constructed.
Key Words: Discrete cosine transform; Fourier-polynomial; Optimality criteria; Resolution; Sensitivity analysis; Simulation model; Williams transformation
Received August 2000. Revised December 2000
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
P. Z. G. Qian Nested Latin hypercube designs Biometrika, December 1, 2009; 96(4): 957 - 970. [Abstract] [PDF] |
||||
![]() |
D. Bingham, R. R. Sitter, and B. Tang Orthogonal and nearly orthogonal designs for computer experiments Biometrika, March 1, 2009; 96(1): 51 - 65. [Abstract] [PDF] |
||||
![]() |
C. D. Lin, R. Mukerjee, and B. Tang Construction of orthogonal and nearly orthogonal Latin hypercubes Biometrika, March 1, 2009; 96(1): 243 - 247. [Abstract] [PDF] |
||||
