A Study on Projection Properties of the 12-Run Plackett-Burman Design

  • Park, Dong-Kwon (Associated professor Department of Statistics Yonsei University)
  • 발행 : 1999.12.01

초록

Non-regular designs such as the Plackett-Burman(PB) design have traditionally been used for screening only main effects because of complex aliasing. But it was found that these designs could be used to estimate the 2-factor interactions as well as main effects through the hidden projection property. The goal of this paper is to propose the estimable model when projecting the 12-run PB design using the algebraic geometric method. The core of this method considers the design as a affine variety and the Grbner basis of the design ideal for this affine variety gives the estimable polynomial models. As the results of applying the 12-run PB design it is actually found that this design has the models not only with 2-factor interactions but with 3-factor. This design is the maximal fan in 4-factor projection.

키워드

참고문헌

  1. Technometrics v.3 The $2^{k-p}$ gractional factorial designs Box, G.E.P.;Hunter, J.S.
  2. Ideal, Variety, and Algorithms Cox, D.;Little, J.;O'Shea, D.
  3. Journal of Quality Technology v.24 Analysis of designed experiments with complex alasing Hamada, M.;Wu, C.F.J.
  4. Technometrics v.34 Projection properties of plackett and Burman designs Lin, D.K.J.;Draper, N.R.
  5. Biometrika v.83 Generalized confounding with Grobner bases Pistone, G.;Wynn, H.P.
  6. Biometrika v.33 The design of optimum multifactorial experiments Plackett, R.L.;Burman, J.P.
  7. Statistica Sinica v.5 A hidden projection property of Plackett-Burman and related designs Wang, J.C.;Jeff Wu, C.F.