Optimal Supersaturated Designs for sm Factorials in N ≢ 0 (mod s) Runs
Abstract
Supersaturated designs (SSDs) offer apotentially useful way to investigate many factors with only a few experiments during the preliminary stages of experimentation. A popular measure to assess multilevel SSDs is the E(χ2) criterion. The literature reports on SSDs have concentrated mainly on balanced designs. For s-level SSDs, the restriction of the number of runs N being only a multiple of s is really not required for the purpose of use of such designs. Just like when N is a multiple of s and the design ensures orthogonality of the factor effects with the mean effect, in the case of N not a multiple of s, we ensure near orthogonality of each of the factors with the mean. In this article we consider s-level E(χ2)-optimal designs for N ≡ n (mod s), 0 ≤ n ≤ s − 1. We give an explicit lower bound on E(χ2). We give the structures of design matrices that attain the lower bounds. Some combinatorial methods for constructing E(χ2)-optimal SSDs are provided.
AMS Subject Classification
62K15Keywords
Effect sparsity Lower bound Screening designs Supersaturated designsPreview
Unable to display preview. Download preview PDF.
References
- Booth, K. H. V., and D. R. Cox. 1962. Some systematic supersaturated designs. Technometrics, 4, 489–495.MathSciNetzbMATHGoogle Scholar
- Box, G. E. P., and R. D. Meyer. 1986. An analysis for unreplicated fractional factorials. Technometrics, 28, 11–18.MathSciNetCrossRefGoogle Scholar
- Bulutoglu, D. A., and C. S. Cheng. 2004. Construction of E(s 2)-optimal supersaturated designs. Ann. Stat., 32, 1662–1678.MathSciNetCrossRefGoogle Scholar
- Bulutoglu, D. A., and K. J. Ryan. 2008. E(s 2)-optimal supersaturated designs with good minimax properties when N is odd. J. Stat. Plan. Inference, 138, 1754–1762.MathSciNetCrossRefGoogle Scholar
- Chai, F. S., K. Chatterjee, and S. Gupta. 2009. Generalized E(s 2) criterion for multilevel supersaturated designs. Commun. Statist. Theory Methods, 38, 1–11.MathSciNetCrossRefGoogle Scholar
- Butler, N. A., R. Mead, K. M. Eskridge, and S. G. Gilmour. 2001. A general method of constructing E(s 2)-optimal supersaturated designs. J. R. Stat. Soc. B, 63, 621–632.MathSciNetCrossRefGoogle Scholar
- Chen, J., and M. Q. Liu. 2008. Optimal mixed-level supersaturated design with general number of runs. Stat. Probab. Lett., 78, 2496–2502.MathSciNetCrossRefGoogle Scholar
- Cheng, C. S. 1997. E(s 2)-optimal supersaturated designs. Stat. Sinica, 7, 929–939.MathSciNetzbMATHGoogle Scholar
- Das, A., A. Dey, L. Y. Chan, and K. Chatterjee. 2008. On E(s 2)-optimal supersaturated designs. J. Stat. Plann. Inference, 138, 3749–3757.MathSciNetCrossRefGoogle Scholar
- Fang, K. T., D. K. J. Lin, and M. Q. Liu. 2003. Optimal mixed-level supersaturated design. Metrika, 58, 279–291.MathSciNetCrossRefGoogle Scholar
- Fang, K. T., D. K. J. Lin, and C. X. Ma. 2000. On the construction of multi-level supersaturated designs. J. Stat. Plan. Inference, 86, 239–252.MathSciNetCrossRefGoogle Scholar
- Li, W. W., and C. F. J. Wu. 1997. Columnwise-pairwise algorithms with applications to the construction of supersaturated designs. Technometrics, 39, 171–179.MathSciNetCrossRefGoogle Scholar
- Li, P. F., M. Q. Liu, R. C. Zhang. 2004. Some theory and the construction of mixed-level supersaturated designs. Statist. Probab. Lett., 69, 105–116.MathSciNetCrossRefGoogle Scholar
- Lin, D. K. J. 1993. A new class of supersaturated designs. Technometrics, 35, 28–31.CrossRefGoogle Scholar
- Lin, D. K. J. 1995. Generating systematic supersaturated designs. Technometrics, 37, 213–225.CrossRefGoogle Scholar
- Liu, Y., and A. Dean. 2004. k-circulant supersaturated designs. Technometrics, 46, 32–43.MathSciNetCrossRefGoogle Scholar
- Liu, Y., and D. K. J. Lin. 2009. Construction of optimal mixed-level supersaturated designs. Stat. Sin., 19, 197–211.MathSciNetzbMATHGoogle Scholar
- Liu, Y., M. Q. Liu, and R. C. Zhang. 2007. Construction of multi-level supersaturated design via Kronecker product. J. Stat. Plan. Inf., 137, 2984–2992.MathSciNetCrossRefGoogle Scholar
- Lu, X., W. Hu, and Y. Zheng. 2003. A systematic procedure in the construction of multi-level supersaturated designs. J. Stat. Plan. Inf., 115, 287–310.CrossRefGoogle Scholar
- Lu, X., Y. Sun. 2001. Supersaturated design with more than two levels. Chin. Ann. Math. Ser. B, 22, 183–194.MathSciNetCrossRefGoogle Scholar
- Mukerjee, R., and C. F. J. Wu. 1995. On the existence of saturated and nearly saturated asymmetrical orthogonal arrays. Ann. Stat., 23, 2102–2115.MathSciNetCrossRefGoogle Scholar
- Nguyen, N. K. 1996. An algorithmic approach to constructing supersaturated designs. Technometrics, 38, 69–73.CrossRefGoogle Scholar
- Nguyen, N. K., and C. S. Cheng. 2008. New E(s 2)-optimal supersaturated designs obtained from incomplete block designs. Technometrics, 50, 26–31.MathSciNetCrossRefGoogle Scholar
- Ryan, K. J., D. A. Bulutoglu. 2007. E(s 2)-optimal supersaturated designs with good minimax properties. J. Stat. Plan. Inference, 137, 2250–2262.MathSciNetCrossRefGoogle Scholar
- Satterthwaite, F. E. 1959. Random balance experimentation. Technometrics, 1, 111–137.MathSciNetCrossRefGoogle Scholar
- Suen, C. Y., and A. Das. 2010. E(s 2)-optimal supersaturated designs with odd number of runs. J. Stat. Plan. Inference, 140.Google Scholar
- Tang, B., and C. F. J. Wu. 1997. A method for constructing supersaturated designs and its E(s 2)-optimality. Can. J. Stat., 25, 191–201.CrossRefGoogle Scholar
- Wu, C. F. J. 1993. Construction of supersaturated designs through partially aliased interactions. Biometrika, 80, 661–669.MathSciNetCrossRefGoogle Scholar
- Wu, C. F. J., and M. Hamada. 2000. Experiments: Planning, analysis and parameter design optimization. New York: Wiley.zbMATHGoogle Scholar
- Xu, H., and C. F. J. Wu. 2005. Construction of optimal multi-level supersaturated designs. Ann. Stat., 33, 2811–2836.MathSciNetCrossRefGoogle Scholar
- Yamada, S., Y. T. Ikebe, H. Hashiguchi, and N. Niki. 1999. Construction of three level supersaturated design. J. Stat. Plan. Inference, 81, 183–193.MathSciNetCrossRefGoogle Scholar
- Yamada, S., D. K. J. Lin. 1999. Three-level supersaturated designs. Stat. Probab. Lett., 45, 31–39.MathSciNetCrossRefGoogle Scholar
- Yamada, S., and T. Matasui. 2002. Optimality of mixed-level supersaturated designs. J. Stat. Plan. Inference, 104, 459–468.MathSciNetCrossRefGoogle Scholar