论文信息 - UNIVERSALLY OPTIMAL DESIGNS FOR COMPUTER EXPERIMENTS

UNIVERSALLY OPTIMAL DESIGNS FOR COMPUTER EXPERIMENTS

The concept of universal optimality from optimum design theory is intro- duced into computer experiments, modeled as realizations of stationary Gaussian processes. When the correlation function is a nondecreasing and convex function of a distance measure, it is shown that a design is universally optimal if it is equidis- tant and of maximum average distance. Examples of universally optimal designs are given with respect to rectangular, Euclidean, Hamming, and Lee distances.

Hongquan Xu | Hongquan Xu

[1] Chandra Satyanarayana. Lee metric codes over integer residue rings (Corresp.) , 1979, IEEE Trans. Inf. Theory.

[2] Elwyn R. Berlekamp,et al. Algebraic coding theory , 1984, McGraw-Hill series in systems science.

[3] J. Kiefer. Construction and optimality of generalized Youden designs II , 1975 .

[4] Rahul Mukerjee,et al. On the existence of saturated and nearly saturated asymmetrical orthogonal arrays , 1995 .

[5] R. J. Martin. Some aspects of experimental design and analysis when errors are correlated , 1982 .

[6] Henry P. Wynn,et al. Maximum entropy sampling , 1987 .

[7] Henry P. Wynn,et al. [Design and Analysis of Computer Experiments]: Rejoinder , 1989 .

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

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

[10] T. J. Mitchell,et al. Bayesian Prediction of Deterministic Functions, with Applications to the Design and Analysis of Computer Experiments , 1991 .

[11] 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.

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