2-수준 요인실험에서 주효과 및 교호작용에 대한 효율적인 분석방법 연구

A Study on Effective Identification Method for Influential Main Effects and Interactions in the 2-level Factorial Designs

  • 김상익 (건국대학교 상경대학 응용통계학과)
  • Kim, Sang-Ik (Dept. of Applied Statistics, KonKuk University)
  • 발행 : 2006.03.31

초록

In this paper, an effective method for identifying influential main effects and interactions in the 2-level factorial designs is suggested by exploiting the resolution V designs developed by Kim(1992). For analysis of such designs, we employ the Bayesian approach for easy and clear identification of influential effects in the half normal probability plot.

키워드

참고문헌

  1. Box, G. E. P. and Hunter, J. S.(1961), 'The $2_{k-p}$ Fractional Factorial Design I', Technometrics, Vol. 3, pp. 311-351 https://doi.org/10.2307/1266725
  2. Box, G. E. P. and Meyer, R. D.(1986), 'An Analysis for Unreplicated Fractional Factorials', Technometrics, Vol. 28, pp. 11-18 https://doi.org/10.2307/1269599
  3. Daniel, C.(1959), 'Use of Half-Normal Plots in Interpreting Factorial Two-Level Experiments', Technometrics, Vol. 1, pp. 311-341 https://doi.org/10.2307/1266715
  4. Length, R. S.(1989), 'Quick and Easy Analysis of Unreplicated Factorials', Technometrics, Vol. 31, pp. 469-473 https://doi.org/10.2307/1269997
  5. Milliken, G. A. and Johnson, D. E.(1989), Analysis of Messy Data, Vol. 2, Chapman & Hall/CRC, Boca Ratom
  6. Montgomery, D. C.(1991), Design and Analysis of Experiments, 3rd edition, Wiley, New York
  7. Neter, J., W. Wasserman, and Kutner, M. H.(1985), Applied Liner Statistical Method, 2nd edition, Richard D. Irwin, Homewood, Illnois
  8. Kim, S. I.(1992), 'Minimal Balanced $2^t$ Fractional Factorial Designs of Resolution V and Taguchi Method', The Korean Journal of Applied Statistics, Vol. 5, pp. 19-28
  9. Kim, S. I.(1994), 'Detection of Influential Interaction Effects in Parameter Design', The Korean Journal of Applied Statistics, Vol. 7, pp. 201-211
  10. Zahn, D. A.(1975), 'Modifications of and Revised Critical Values for the Half-Normal Plot', Technometrics, Vol. 17, pp. 189-200 https://doi.org/10.2307/1268351