Maximum projection designs for computer experiments

被引:241
作者
Joseph, V. Roshan [1 ]
Gul, Evren [1 ]
Ba, Shan [2 ]
机构
[1] Georgia Inst Technol, H Milton Stewart Sch Ind & Syst Engn, Atlanta, GA 30332 USA
[2] Procter & Gamble Co, Mason, OH 45040 USA
关键词
Experimental design; Gaussian process; Latin hypercube design; Screening design; Space-filling design;
D O I
10.1093/biomet/asv002
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Space-filling properties are important in designing computer experiments. The traditional maximin and minimax distance designs consider only space-filling in the full-dimensional space; this can result in poor projections onto lower-dimensional spaces, which is undesirable when only a few factors are active. Restricting maximin distance design to the class of Latin hypercubes can improve one-dimensional projections but cannot guarantee good space-filling properties in larger subspaces. We propose designs that maximize space-filling properties on projections to all subsets of factors. We call our designs maximum projection designs. Our design criterion can be computed at no more cost than a design criterion that ignores projection properties.
引用
收藏
页码:371 / 380
页数:10
相关论文
共 13 条
[1]  
[Anonymous], 1987, Journal of Applied Statistics, DOI DOI 10.1080/02664768700000020
[2]  
[Anonymous], 2015, R LANG ENV STAT COMP
[3]  
[Anonymous], 2015, MaxPro: Maximum projection designs
[4]  
Ba S., 2015, SLHD MAXIMIN DISTANC
[5]   Generalized Latin Hypercube Design for Computer Experiments [J].
Dette, Holger ;
Pepelyshev, Andrey .
TECHNOMETRICS, 2010, 52 (04) :421-429
[6]   Noncollapsing Space-Filling Designs for Bounded Nonrectangular Regions [J].
Draguljic, Danel ;
Santner, Thomas J. ;
Dean, Angela M. .
TECHNOMETRICS, 2012, 54 (02) :169-178
[7]   A generalized discrepancy and quadrature error bound [J].
Hickernell, FJ .
MATHEMATICS OF COMPUTATION, 1998, 67 (221) :299-322
[8]   MINIMAX AND MAXIMIN DISTANCE DESIGNS [J].
JOHNSON, ME ;
MOORE, LM ;
YLVISAKER, D .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1990, 26 (02) :131-148
[9]   Design and analysis of computer experiments [J].
Kuhnt, Sonja ;
Steinberg, David M. .
ASTA-ADVANCES IN STATISTICAL ANALYSIS, 2010, 94 (04) :307-309
[10]   A COMPARISON OF THREE METHODS FOR SELECTING VALUES OF INPUT VARIABLES IN THE ANALYSIS OF OUTPUT FROM A COMPUTER CODE [J].
MCKAY, MD ;
BECKMAN, RJ ;
CONOVER, WJ .
TECHNOMETRICS, 1979, 21 (02) :239-245