DOI QR코드

DOI QR Code

A comparison of models for the quantal response on tumor incidence data in mixture experiments

계수적 반응을 갖는 종양 억제 혼합물 실험에서 모형 비교

  • Kim, Jung Il (Department of Information Statistics, Kangwon National University)
  • Received : 2017.08.21
  • Accepted : 2017.09.19
  • Published : 2017.09.30

Abstract

Mixture experiments are commonly encountered in many fields including food, chemical and pharmaceutical industries. In mixture experiments, measured response depends on the proportions of the components present in the mixture and not on the amount of the mixture. Statistical analysis of the data from mixture experiments has mainly focused on a continuous response variable. In the example of quantal response data in mixture experiments, however, the tumor incidence data have been analyzed in Chen et al. (1996) to study the effects of 3 dietary components on the expression of mammary gland tumor. In this paper, we compared the logistic regression models with linear predictors such as second degree Scheffe polynomial model, Becker model and Akay model in terms of classification accuracy.

화학, 제약, 식품 등 여러 분야에서 활용되는 혼합물 실험은 반응변수가 설명변수들의 절대량이 아닌 상대적인 혼합비율에 의해 영향을 받고 구조상 공선성이 존재하게 되는 성질이 있으며 양적인 반응변수들에 대한 실험이 많아 대부분 정규분포를 가정하고 선형모형을 적용하여 분석하고 있다. 이 논문에서는 반응변수가 계수형인 혼합물 실험의 사례로 Chen 등(1996)에 소개된 종양 억제 효과에 대한 실험에 나타난 지방, 탄수화물, 섬유질과 같은 식이요법 관련 혼합물 성분들과 종양 발현 여부인 계수형 방응변수를 갖는 자료를 대상으로 셰페의 2차 다항모형과 성분들간의 비선형적 관계를 보완하기 위해 대안으로 제시된 베커의 수정 모형들, 그리고 공선성을 완화하기 위해 제시된 Akay와 Tez(2011)의 성분비 변환 모형을 설명변수들의 선형결합으로 활용하여 설정한 로지스틱회귀모형들을 분류 정확도 기준을 적용하여 비교하고 결과를 설명하였다.

Keywords

References

  1. Akay, K. U. and Tez, M (2011). Alternative modeling techniques for the quantal response data in mixture experiments. Journal of Applied Statisitics, 36, 373-390.
  2. Becker, N. G. (1968). Models for the response of mixture. Journal of Royal Statistical Society B, 30, 349-358.
  3. Chen, J. J., Li, L. A. and Jackson, C. D. (1996). Analysis of quantal response data from mixture experiments. Environmetrics, 7, 503-512. https://doi.org/10.1002/(SICI)1099-095X(199609)7:5<503::AID-ENV227>3.0.CO;2-E
  4. Cornell J. A. (2002). Experiments with mixtures, John Wiley & Sons, Inc., New York.
  5. Hong, C. S. and Wu, Z. Q. (2014). Alternative accuracy for multiple ROC analysis. Journal of the Korean Data & Information Science Society, 25, 1521-1530. https://doi.org/10.7465/jkdi.2014.25.6.1521
  6. Hong, C. S. and Yang, D. S. (2015). ROC curve and AUC for linear growth models. Journal of the Korean Data & Information Science Society, 26, 1367-1375. https://doi.org/10.7465/jkdi.2015.26.6.1367
  7. Jang, D. H. and Anderson-Cook, C. M. (2011). Fraction of design space plots for evaluating ridge estimators in mixture experiments. Quality and Reliability Engineering International , 27, 27-34. https://doi.org/10.1002/qre.1104
  8. Jang, D. H. and Yoon, M. (1997). Graphical methods for evaluating ridge regression estimator in mixture experiments. Communications in Statistics-Simulations and Computation, 26, 1049-1061. https://doi.org/10.1080/03610919708813425
  9. Park, C. and Kye, M. J. (2013). Penalized logistic regression models for determining the discharge of dyspnea patients. Journal of the Korean Data & Information Science Society, 24, 125-133. https://doi.org/10.7465/jkdi.2013.24.1.125