The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Firework plot for evaluating the impact of influential observations in multi-response surface methodology

다반응 반응표면분석에서 특이값의 영향을 평가하기 위한 불꽃그림

  • Kim, Sang Ik (Department of Applied Statistics, Konkuk University) ;
  • Jang, Dae-Heung (Department of Statistics, Pukyong National University)
  • 김상익 (건국대학교 응용통계학과) ;
  • 장대흥 (부경대학교 통계학과)
  • Received : 2017.10.31
  • Accepted : 2017.12.20
  • Published : 2018.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

It has been routine practice in regression analysis to check the validity of the assumed model by the use of regression diagnostics tools. Outliers and influential observations often distort the regression output in an undesired manner. Jang and Anderson-Cook (Quality and Reliability Engineering International, 30, 1409-1425, 2014) proposed a graphical method (called a firework plot) so that there could be an exploratory visualization of the trace of the impact of the possible outliers and influential observations on individual regression coefficients and the overall residual sum of the squares measure. This paper further extends a graphical approach to a multi-response surface methodology problem.

회귀모형을 이용하여 자료를 분석하는 경우 이상점이나 영향점의 유무를 검정하는 회귀진단기법은 모형의 적합성을 체크하기 위한 필수적인 도구이다. 이러한 이상점이나 영향점이 존재하는 경우 회귀분석의 결과가 왜곡되어 해석이 된다. Jang과 Anderson-Cook (Quality and Reliability Engineering International, 30, 1409-1425, 2014)은 불꽃그림이란 이름을 붙인 그래픽 방법를 제시하였는데 관측값에 부여된 가중치를 1에서 0으로 변화함에 따라 이상점이나 영향점이 회귀계수 및 잔차제곱합에 어떠한 영향을 미치는지 살펴 보았다. 본 연구에서는 다반응 반응표면분석에서 이러한 불꽃그림을 적용하여 보고자 한다.

Keywords

References

  1. Beckman, R. J. and Cook, R. D. (1983). Outlier ... ... ... s, Technometrics, 25, 119-147.
  2. Belsley, D. A., Kuh, E., and Welch, R. E. (1980). Regression Diagnostics: Identifying In uential Data and Source of Collinearity, Wiley, New York.
  3. Cook, R. D. (1977). Detection of influential observation in linear regression, Technometrics, 19, 15-18.
  4. Cook, R. D. (1979). Influential observation in linear regression, Journal of American Statistical Association, 74, 169-174. https://doi.org/10.1080/01621459.1979.10481634
  5. Cook, R. D. and Weisberg, S. (1989). Regression diagnostics with dynamic graphics, Technometrics, 31, 277-291.
  6. Emerson, J. D. and Strenio, J. (1983). The Spread-versus-Level plot. In Hoaglin, D. C., Mosteller, F., and Tukey, J. W. (eds), Understanding Robust and Exploratory Data analysis, Wiley, New York.
  7. Fox, J. (2008). Applied Regression Analysis and Generalized Linear Models (2nd ed), Sage, New York.
  8. Jang, D. H. and Anderson-Cook C. M. (2014). Firework plot as a graphical exploratory data analysis tool for evaluating the impact of outliers in data exploration and regression, Quality and Reliability Engineering International, 30, 1409-1425. https://doi.org/10.1002/qre.1563
  9. Kim, C., Lee, J., Yang, H., and Bae, W. (2015). Case influence diagnostics in the lasso regression, Journal of the Korean Statistical Society, 44, 271-279. https://doi.org/10.1016/j.jkss.2014.09.003
  10. Myers, R. H., Montgomery, D. C., and Anderson-Cook, C. M. (2016). Response Surface Methodology: Process and Product Optimization Using Designed Experiments (4th ed), Wiley, New York.
  11. Park, S. H., Kim, Y. H., and Toutenberg, H. (1992). Regression diagnostics for removing an observation with animating graphics, Statistical Papers, 33, 227-240. https://doi.org/10.1007/BF02925327
  12. Zhao, J., Leng, C., Li, L., andWang, H. (2013). High-dimensional influence measure, The Annals of Statistics, 41, 2639-2667. https://doi.org/10.1214/13-AOS1165