A CASE STUDY IN THE APPLICATION OF SUPERSATURATED DESIGNS TO COMPUTER EXPERIMENTS

Supersaturated design is essentially a fractional factorial design in which the number of potential effects is greater than the number of runs. In this article, the supersaturated design is applied to a computer experiment through an example of steady current circuit model problem. A uniform mixed-level supersaturated design and the centered quadratic regression model are used. This example shows that supersaturated design and quadratic regression modeling method are very effective for screening effects and building the predictor. They are not only useful in computer experiments but also in industrial and other scientific experiments.

COMPUTATION OF THE E(s^2) VALUES OF SOME E(s^2) OPTIMAL SUPERSATURATED DESIGNS

A supersaturated design is a design whose run size is not enough for estimating all the main effects represented by the columns of the design matrix. It is widely used in the preliminary stages of industrial statistics and other scientific experiments. In this paper, formulas for computing the E(s2) values of E(s2) optimal supersaturated designs with m = t(n - 1) ± e(e = 1 and 2) are given, and the accuracy and convenience of using these formulas are demonstrated by an example.

A two-stage variable selection strategy for supersaturated designs with multiple responses

A supersaturated design （SSD）, whose run size is not enough for estimating all the main effects, is commonly used in screening experiments. It offers a potential useful tool to investigate a large number of factors with only a few experimental runs. The associated analysis methods have been proposed by many authors to identify active effects in situations where only one response is considered. However, there are often situations where two or more responses are observed simultaneously in one screening experiment, and the analysis of SSDs with multiple responses is thus needed. In this paper, we propose a two-stage variable selection strategy, called the multivariate partial least squares-stepwise regression （MPLS-SR） method, which uses the multivariate partial least squares regression in conjunction with the stepwise regression procedure to select true active effects in SSDs with multiple responses. Simulation studies show that the MPLS-SR method performs pretty good and is easy to understand and implement.

A Note on Supersaturated Design

Supersaturated designs are common choice for screening experiments.This paper studies the properties of supersaturated designs.We give new lower bounds of E(s^(2))-criterion and E(f_(NOD))-criterion.Some linkages between the combined/double design and its original design are firstly provided,and the lower bounds of E(s^(2)) and E(f_(NOD)) for the combined/double design are also given.Furthermore,the close relationship between the minimum Lee-moment aberration criterion and the criteria for optimal supersaturated designs is revealed.These theoretical results can be used to construct or search for optimal supersaturated designs in practice.Numerical results are also provided,which lend further support to our theoretical findings.

Construction of Optimal Mixed-Level Uniform Designs

The theory of uniform design has received increasing interest because of its wide application in the field of computer experiments.The generalized discrete discrepancy is proposed to evaluate the uniformity of the mixed-level factorial design.In this paper,the authors give a lower bound of the generalized discrete discrepancy and provide some construction methods of optimal mixed-level uniform designs which can achieve this lower bound.These methods are all deterministic construction methods which can avoid the complexity of stochastic algorithms.Both saturated mixed-level uniform designs and supersaturated mixed-level uniform designs can be obtained with these methods.Moreover,the resulting designs are also χ^(2)-optimal and minimum moment aberration designs.