Chung-yi Suen

E(s2)-optimal supersaturated designs with odd number of runs

A popular measure to assess 2-level supersaturated designs with even number of runs is the E(s2)E(s2) criterion. In this paper, we consider 2-level supersaturated designs with odd number of runs which have minimum E(s2)E(s2). We give a more explicit lower bound on E(s2)E(s2) than Bulutoglu and Ryan (2008). Conditions of supersaturated designs which attain the lower bounds are given. E(s2)-optimalE(s2)-optimal supersaturated designs attaining the lower bounds are listed for n=5n=5 and 7. Hadamard matrices and finite fields are used for constructing E(s2)-optimalE(s2)-optimal supersaturated designs. The lower bound is improved when the number of factors is large, and designs attaining the improved bounds are constructed by using the complements of designs with small number of factors. We also give a method to construct E(s2)-optimalE(s2)-optimal supersaturated designs with odd number of runs from E(s2)-optimalE(s2)-optimal supersaturated designs with even number of runs by deleting a run.

Construction of asymmetric orthogonal arrays through finite geometries

Finite geometries are used to construct several families of asymmetric orthogonal arrays. Many of these arrays appear to be new.

Some rectangular designs constructed by the method of differences

Abstract Some new series of rectangular designs are constructed by the method of differences.

Further results on orthogonal array plus one run plans

This paper considers the issue of optimality of orthogonal array plus one run plans under generalized criteria of type 1 which include the D-, A-, and E-criteria. Our results, in conjunction with those in Mukerjee (Ann. Statist.) cover all orthogonal arrays of strength two and involving up to 100 rows, except perhaps those having 72 rows, and thus almost completely settle the problem for resolution III plans over a practical range.

A class of orthogonal main-effect plans

Abstract A class of orthogonal main-effect plans for 2 m q k · q 2 m q k ( m ≤2 k and q a prime power) experiments is constructed by using generalized Hadamard matrices. Other useful orthogonal main-effect plans for asymmetrical factorial experiments can be constructed by collapsing the 2 m q k -level factor. All the plans constructed are saturated and provide orthogonal estimates of the mean and all main effects when all interactions are assumed to be zero.

E(s2)-optimalE(s2)-optimal supersaturated designs with odd number of runs

A popular measure to assess 2-level supersaturated designs with even number of runs is the E(s2)E(s2) criterion. In this paper, we consider 2-level supersaturated designs with odd number of runs which have minimum E(s2)E(s2). We give a more explicit lower bound on E(s2)E(s2) than Bulutoglu and Ryan (2008). Conditions of supersaturated designs which attain the lower bounds are given. E(s2)-optimalE(s2)-optimal supersaturated designs attaining the lower bounds are listed for n=5n=5 and 7. Hadamard matrices and finite fields are used for constructing E(s2)-optimalE(s2)-optimal supersaturated designs. The lower bound is improved when the number of factors is large, and designs attaining the improved bounds are constructed by using the complements of designs with small number of factors. We also give a method to construct E(s2)-optimalE(s2)-optimal supersaturated designs with odd number of runs from E(s2)-optimalE(s2)-optimal supersaturated designs with even number of runs by deleting a run.

supersaturated designs with odd number of runs

A popular measure to assess 2-level supersaturated designs with even number of runs is the E(s2)E(s2) criterion. In this paper, we consider 2-level supersaturated designs with odd number of runs which have minimum E(s2)E(s2). We give a more explicit lower bound on E(s2)E(s2) than Bulutoglu and Ryan (2008). Conditions of supersaturated designs which attain the lower bounds are given. E(s2)-optimalE(s2)-optimal supersaturated designs attaining the lower bounds are listed for n=5n=5 and 7. Hadamard matrices and finite fields are used for constructing E(s2)-optimalE(s2)-optimal supersaturated designs. The lower bound is improved when the number of factors is large, and designs attaining the improved bounds are constructed by using the complements of designs with small number of factors. We also give a method to construct E(s2)-optimalE(s2)-optimal supersaturated designs with odd number of runs from E(s2)-optimalE(s2)-optimal supersaturated designs with even number of runs by deleting a run.