DOI QR코드

DOI QR Code

Power comparison for 3×3 split plot factorial design

3×3 분할요인모형의 검정력 비교연구

  • 최영훈 (한신대학교 응용통계학과)
  • Received : 2016.12.27
  • Accepted : 2017.01.17
  • Published : 2017.01.31

Abstract

Restriction of completely randomization within a block can be handled by a split plot factorial design splitted by several plots. $3{\times}3$ split plot factorial design with two fixed main factors and one fixed block shows that powers of the rank transformed statistic for testing whole plot factorial effect and split plot factorial effect are superior to those of the parametric statistic when existing effect size is small or the remaining effect size is relatively smaller than the testing factorial effect size. Powers of the rank transformed statistic show relatively high level for exponential and double exponential distributions, whereas powers of the parametric and rank transformed statistic maintain similar level for normal and uniform distributions. Powers of the parametric and rank transformed statistic with two fixed main factors and one random block are respectively lower than those with all fixed factors. Powers of the parametric andrank transformed statistic for testing split plot factorial effect with two fixed main factors and one random block are slightly lower than those for testing whole plot factorial effect, but powers of the rank transformed statistic show comparative advantage over those of the parametric statistic.

블럭내의 완전랜덤화 제약은 하나의 블럭이 여러 실험구로 분할되는 분할요인모형으로 해결할 수 있다. 본 연구는 $3{\times}3$ 분할요인모형에서 두 주요인 및 하나의 블럭이 모두 고정일 경우에는, 실제로 존재하는 효과크기가 작을수록 혹은 검정대상의 요인효과 크기보다 검정대상 이외의 효과들의 크기가 상대적으로 작을수록 주구요인효과 및 세구요인효과 검정을 위한 순위변환 통계량의 검정력은 기존의 모수적 통계량의 검정력보다 뛰어남을 알 수 있다. 또한 모집단 모형의 오차항이 지수분포 및 이중지수분포일 때 효과크기 및 효과구성유형에 상관없이 거의 모든 상황하에서 순위변환 통계량의 검정력이 모수적 통계량의 검정력보다 상대적으로 높은 우위를 보이며, 정규분포 및 균일분포하에서는 상당히 유사한 수준을 나타낸다. 한편 두 주요인은 고정이나 하나의 블럭이 랜덤일 경우에는, 두 주요인 및 블럭이 모두 고정일 경우보다 모수적 통계량 및 순위변환 통계량의 검정력은 각각 낮은 수준을 보인다. 특히 주구요인효과 검정보다 세구요인효과 검정을 위한 모수적 통계량 및 순위변환 통계량의 검정력이 다소 낮은 수준임을 보이지만, 순위변환 통계량의 검정력은 모수적 통계량의 검정력에 비하여 높은 상대적 검정력 우위를 나타낸다.

Keywords

References

  1. Akritas, M. G. and Papadatos, N. (2004). Heteroscedastic one way ANOVA and lack of fit tests. Journal of the American Statistical Association, 99, 368-382. https://doi.org/10.1198/016214504000000412
  2. Blair, R. C., Sawilowsky, S. S. and Higgins, J. J. (1989). An investigation of the type I error and power properties of the rank transform procedure in factorial ANOVA. Journal of Educational Statistics, 14, 255-267. https://doi.org/10.3102/10769986014003255
  3. Choi, J. (2015). Projection analysis for balanced incomplete block designs. Journal of the Korean Data & Information Science Society, 26, 347-354. https://doi.org/10.7465/jkdi.2015.26.2.347
  4. Choi, Y. H. (1998). A study of the power of the rank transform test in a 2(3) factorial experiment. Communications in Statistics, 27, 251-266.
  5. Choi, Y. H. (2014). Power study for 2$\times$2 factorial design in 4$\times$4 latin square design. Journal of the Korean Data & Information Science Society, 25, 1195-1205. https://doi.org/10.7465/jkdi.2014.25.6.1195
  6. Conover, W. J. and Iman, R. L. (1981). Rank transformations as a bridge between parametric and nonparametric statistics. The American Statistician, 35, 124-128.
  7. Fabian, V. (1991). On the problem of interactions in the analysis of variance. Journal of the American Statistical Association, 86, 362-374. https://doi.org/10.1080/01621459.1991.10475048
  8. Gorman, J. O. and Akritas, M. G. (2001). Nonparametric models and methods for designs with dependent censored data. Biometrics, 57, 88-95. https://doi.org/10.1111/j.0006-341X.2001.00088.x
  9. Hicks, C. R. (1982). Fundamental concepts in the design of experiments, 3rd Ed., Holt, Rinehart and Winston, New York.
  10. Jo, S. and Kim, D. (2013). Nonparametric procedures using aligned method and joint placement in randomized block design. Journal of the Korean Data & Information Science Society, 24, 95-103. https://doi.org/10.7465/jkdi.2013.24.1.95
  11. Montgomery, D. C. (1991). Design and analysis of experiments, 3rd Ed., John Wiley & Sons, New York.
  12. Neter, J., Wasserman, W. and Kutner, M. H. (1990). Applied linear statistical model, 3rd Ed., Irwin, Homewood and Boston.
  13. Pavur, R. and Nath, R. (1986). Parametric versus rank transform procedures in the two-way factorial experiment. Journal of Statistical Computation Simulation, 23, 231-240. https://doi.org/10.1080/00949658608810873
  14. Woo, H. and Park, S. (2014). Statistical procedures of add-on trials for bioequivalence in 2$\times$k crossover designs. Journal of the Korean Data & Information Science Society, 25, 1181-1193. https://doi.org/10.7465/jkdi.2014.25.6.1181