DOI QR코드

DOI QR Code

AROC 곡선과 최적분류점

AROC Curve and Optimal Threshold

  • 홍종선 (성균관대학교 통계학과) ;
  • 이희정 (성균관대학교 응용통계연구소)
  • Hong, Chong-Sun (Department of Statistics, Sungkyunkwan University) ;
  • Lee, Hee-Jung (Research Institute of Applied Statistics, Sungkyunkwan University)
  • 투고 : 20100800
  • 심사 : 20101000
  • 발행 : 2011.02.28

초록

혼합분포를 가정한 신용평가 연구에서 ROC 곡선은 부도와 정상 차주의 판별력을 탐색하는데 유용한 그림이다. ROC 곡선을 개선하여 스코어를 파악할 수 있는 AROC 곡선을 수리적으로 분석하고, 정규분포를 적용하여 다양한 곡선의 형태를 파악한다. 최적분류점을 발견하는 다양한 분류정확도 통계량과 AROC 곡선의 관계를 발견하고, 두 분포의 분산이 동일한 경우에 AROC 곡선의 극소점으로 최적의 분류점을 추정할 수 있음을 발견한다.

In the credit evaluation study with the assumption of mixture distributions, the ROC curve is a useful method to explore the discriminatory power of default and non-default borrowers. The AROC curve is an adjusted ROC curve that can be identified with the corresponding score and is mathematically analyzed in this work. We obtain patterns of this curve by applying normal distributions. Moreover, the relationship between the AROC curve and many classification accuracy statistics are explored to find the optimal threshold. In the case of equivalent variances of two distributions, we obtain that the local minimum of the AROC curve is estimated at the optimal threshold to maximize certain classification accuracies.

키워드

참고문헌

  1. 홍종선, 김지훈, 최진수 (2009). 조정된 ROC와 CAP 곡선, <응용통계연구>, 22, 29-39. https://doi.org/10.5351/KJAS.2009.22.1.029
  2. 홍종선, 주재선, 최진수 (2010). 혼합분포에서 최적분류점, <응용통계연구>, 23, 13-28. https://doi.org/10.5351/KJAS.2010.23.1.013
  3. 홍종선, 최진수 (2009). ROC와 CAP 곡선에서의 최적 분류점, <응용통계연구>, 22, 911–921. https://doi.org/10.5351/KJAS.2009.22.5.911
  4. Bairagi, R. and Suchindran, C. M. (1989). An estimator of the cutoff point maximizing sum of sensitivity and specificity, The Indian Journal of Statistics, 51, 263-269.
  5. Hanley, J. A. and McNeil, B. J. (1982). The meaning and use of the area under a receiver operating characteristic(ROC) curve, Diagnostic Radialogy, 143, 29-36.
  6. Perkins, N. J. and Schisterman, E. F. (2006). The inconsistency of Optimal cutpoints obtained using two criteria and based on the receiver operating characteristic curve, American Journal of Epidemiology, 163, 670-675. https://doi.org/10.1093/aje/kwj063
  7. Sobehart, J. R. and Keenan, S. C. (2001). Measuring Default Accurately, Credit Risk Special Report, Risk, 14, 31–33.
  8. Sobehart, J. R., Keenan, S. C. and Stein, R. M. (2000). Benchmarking Quantitative Default Risk Models: A Validation Methodology, Moody's Investors Service.
  9. Vuk. M. and Curk, T. (2006). Roc curve, lift chart and calibration plot, Metodoloski Zvezki, 3, 89-108.
  10. Youden, W. J. (1950). An index for rating diagnostic tests, Cancer, 3, 32–35.