Advertisement

Journal of Statistical Theory and Practice

, Volume 6, Issue 1, pp 190–203 | Cite as

Characterization of Balanced Second-Order Designs for 3m Factorials

Article

Abstract

We consider a fractional 3m factorial design for the second-order model derived from a simple array (SA), where m ≥ 4. In this article, we give a necessary and sufficient condition for an SA to be a balanced second-order design for 3m factorials. Such a design is characterized by the suffixes of the index of an SA.

AMS Subject Classification

62K15 05B30 

Keywords

BSO design Factorial effect MDR algebra Quadratic equation Row rank SA Second-order model 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Chakravarti, I. M. 1956. Fractional replication in asymmetrical factorial designs and partially balanced arrays. Sankhyā, 17, 143–164.MathSciNetMATHGoogle Scholar
  2. Hoke, A. T. 1974. Economical second-order designs based on irregular fractions of the 3n factorial. Technometrics, 16, 375–384.MathSciNetMATHGoogle Scholar
  3. Hoke, A. T. 1975. The characteristic polynomial of the information matrix for second-order models. Ann. Stat., 3, 780–786.MathSciNetCrossRefGoogle Scholar
  4. James, A. T. 1957. The relationship algebra of an experimental design. Ann. Math. Stat., 28, 993–1002.MathSciNetCrossRefGoogle Scholar
  5. Kuwada, M. 1979a. Balanced arrays of strength 4 and balanced fractional 3m factorial designs. J. Stat. Plan. Inference, 3, 347–360.MathSciNetCrossRefGoogle Scholar
  6. Kuwada, M. 1979b. Optimal balanced fractional 3m factorial designs of resolution V and balanced third-order designs. Hiroshima Math. J., 9, 347–450.MathSciNetMATHGoogle Scholar
  7. Kuwada, M. 1981. Characteristic polynomials of the information matrices of balanced fractional 3m factorial designs of resolution V. J. Stat. Plan. Inference, 5, 189–209.MathSciNetCrossRefGoogle Scholar
  8. Kuwada, M. 1993. Some non-aliasing relationship for second-order model when information matrix is nonsingular. Calcutta Stat. Assoc, Bull., 43, 213–229.CrossRefGoogle Scholar
  9. Kuwada, M., Y. Hyodo, and E. Taniguchi. 2009. Balanced second-order designs of resolutions R(10 ∪ S|Ω) for 3m series. J. Stat. Appl., 4, 339–368.MATHGoogle Scholar
  10. Kuwada, M., and R. Nishii. 1979. On a connection between balanced arrays and balanced fractional sm factorial designs. J. Japan Stat. Soc., 9, 93–101.Google Scholar
  11. Srivastava, J. N., and D. V. Chopra. 1971. On the characteristic roots of the information matrix of 2m balanced factorial designs of resolution V, with applications. Ann. Math. Stat., 42, 722–734.CrossRefGoogle Scholar
  12. Yamamoto, S., Y. Fujii, Y. Hyodo, and T. Yamada. 1990. Bounds on number of constraints for three-symbol balanced arrays. SUT J. Math., 26, 111–141.MathSciNetMATHGoogle Scholar
  13. Yumiba, H., and Y. Hyodo. 2011. Characterization of balanced fractional 3m factorial designs of resolution III. Commun. Stat. Theory Methods, 40, 2074–2080.CrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2012

Authors and Affiliations

  • Hiromu Yumiba
    • 1
  • Yoshifumi Hyodo
    • 1
    • 2
  • Masahide Kuwada
    • 1
    • 3
  1. 1.International Institute for Natural SciencesKurashikiJapan
  2. 2.Graduate School of InformaticsOkayama University of ScienceOkayamaJapan
  3. 3.Graduate School of EngineeringHiroshima UniversityHigashi-HiroshimaJapan

Personalised recommendations