DOI QR코드

DOI QR Code

Two Bootstrap Confidence Intervals of Ridge Regression Estimators in Mixture Experiments

혼합물실험에서 능형회귀추정량에 대한 두 종류의 붓스트랩 신뢰구간

  • Jang Dae-Heung (Division of Mathematical Science, Pukyong National University)
  • 장대흥 (부경대학교 수리과학부 통계학전공)
  • Published : 2006.07.01

Abstract

In mixture experiments, performing experiments in highly constrained regions causes collinearity problems. We can use the ridge regression as a means for stabilizing the coefficient estimators in the fitted model. But there is no theory available on which to base statistical inference of ridge estimators. The bootstrap technique could be used to seek the confidence intervals for ridge estimators.

혼합물실험에서 제한된 영역 때문에 공선성문제가 발생하면 회귀계수에 대한 추정값이 매우 불안정하게 되므로 이를 해결하기 위하여 우리는 주로 능형추정량을 사용한다. 이 때 붓스트랩 기법을 사용하면 능형추정량에 대한 붓스트랩 신뢰구간을 구할 수 있다. 본 논문에서는 제한된 영역을 갖는 혼합물실험의 한 예를 통하여 붓스트랩 잔차 방법과 붓스트랩 쌍 방법 각각에 대하여 능형회귀추정량에 대한 붓스트랩 신뢰구간을 구하고 서로 비교하였다.

Keywords

References

  1. Cornell, J. (2002). Experiments with Mixture, John Wiley & Sons, Inc., New York
  2. Kazami, C. and Brownstone, D. (1999). Bootstrap confidence bands for shrinkage estimators, Journal of Econometrics, 90, 99-127 https://doi.org/10.1016/S0304-4076(98)00037-2
  3. Montgomery, D. C, Peck, E. A., and Vining, G. G. (2001). Introduction to Linear Regression Analysis, John Wiley & Sons, Inc., New York
  4. Politis, D. N., Romano, J. P., and Wolf, M. (1999). Subsampling, Springer, New York
  5. Snee, R. D. (1975). Experimental designs for quadratic models in constrained mixture spaces, Technometrics, 17, 149-159 https://doi.org/10.2307/1268345
  6. St. John, R. C. (1984). Experiments with mixture, ill-conditioning, and ridge regression, Journal of Quality Technology, 16, 81-96 https://doi.org/10.1080/00224065.1984.11978895
  7. Vinod, H. D. (1995). Double bootstrap for shrinkage estimators, Journal of Econometrics, 68, 287-302 https://doi.org/10.1016/0304-4076(94)01639-H

Cited by

  1. Analysis of the Statistical Techniques and Errors in the Field of Sasang Constitution Researches: from 2011 to 2015 vol.28, pp.1, 2016, https://doi.org/10.7730/JSCM.2016.28.1.51