Journal of Statistical Theory and Practice

, Volume 7, Issue 2, pp 345–359 | Cite as

Optimal Cutpoint Estimation With Censored Data

  • Camelia S. SimaEmail author
  • Mithat Gönen


Maximal chi-squared methods and receiver operating characteristic (ROC) curves-based methods are commonly used to dichotomize a continous predictor when the outcome is binary. In this article we consider this problem when the outcome of interest is subject to right censoring, with a twofold goal. First, we propose maximal concordance, a measure similar to the area under an ROC curve, as a metric for selecting an optimal cutpoint with censored endpoints. To support this, we show that selecting the cutpoint that maximizes the concordance probability is equivalent to maximizing the Youden index, a popular criterion when the ROC curve is used to choose a threshold with binary outcomes. Second, we compare the performance of two concordance-based metrics (c-index and concordance probability estimate) and the performance of three chi-squared-based metrics (Wald, log-rank, and partial likelihood ratio statistics). In our simulations performed under a variety of assumptions, maximizing the partial likelihood ratio test statistic has the best performance.


Threshold Survival ROC curve Concordance Maximal chi-squared 

AMS Subject Classification

62N01 62P01 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Altman, D. G. 1994. Problems in dichotomizing continuous variables. Am. J. Epidemiolo., 139, 442–445.CrossRefGoogle Scholar
  2. Begg, C. B., L. D. Cramer, E. S. Venkatraman, and V. Rosai. 2000. Comparing tumour staging and grading systems: A case study and a review of the issues, using thymoma as a model. Stat. Med., 19, 1997–2014.CrossRefGoogle Scholar
  3. Benowitz, N. L., J. T. Bernert, R. S. Caraballo, D. B. Holiday, and J. Wang. 2009. Optimal serum cotinine levels for distinguishing cigarette smokers and nonsmokers within different racial/ethnic groups in the United States between 1999 and 2004. Am. J. Epidemiol., 169, 236–248.CrossRefGoogle Scholar
  4. Bou-Hamad, I., D. Larocque, and H. Ben-Ameur. 2011. A review of survival trees. Statist. Surv., 5, 44–71.MathSciNetCrossRefGoogle Scholar
  5. Cai, T., M. S. Pepe, Y. Zheng, T. Lumley, and N. S. Jenny. 2006. The sensitivity and specificity of markers for event times. Biostatistics, 7, 182–197.CrossRefGoogle Scholar
  6. Colt, J. S. R. K. Severson, J. Lubin, N. Rothman, D. Camann, S. Davis, J. R. Cerhan, W. Cozen, and P. Hartge. 2005. Organochlorines in carpet dust and non-Hodgkin lymphoma. Epidemiology, 16(4), 103–112.CrossRefGoogle Scholar
  7. Cox, D. R. 1972. Regression models and life tables (with discussion). J. R. Stat. Soc. Ser. B, 34, 187–220.zbMATHGoogle Scholar
  8. Efron, B. 1987. Better bootstrap confidence intervals. J. Am. Stat. Assoc., 82, 171–185.MathSciNetCrossRefGoogle Scholar
  9. Efron, B., and R. J. Tibshirani. 1993. An introduction to the bootstrap. Boca Raton, FL, Chapman and Hall.CrossRefGoogle Scholar
  10. Engel, L. S., Q. Lan, and N. Rothman. 2007. Polychlorinated biphenyls and non-Hodgkin lymphoma. Cancer Epidemiol. Biomarkers Prevent., 16, 373–376.CrossRefGoogle Scholar
  11. Gönen, M., and G. Heller. 2005. Concordance probability and discriminatory power in proportional hazards regression. Biometrika, 92, 965–970.MathSciNetCrossRefGoogle Scholar
  12. Harrell, F. E., Jr, K. L. Lee, R. M. Califf, D. B. Pryor, and R. A. Rosati. 1984. Regression modelling strategies for improved prognostic prediction. Stat. Med., 3, 143–152.CrossRefGoogle Scholar
  13. Harrell, F. E. Jr., K. L. Lee, and D. B. Mark. 1996. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat. Med., 15, 361–387.CrossRefGoogle Scholar
  14. Heagerty, P. J., T. Lumley, and M. S. Pepe. 2000. Time-dependent ROC curves for censored survival data and a diagnostic marker. Biometrics, 56, 337–344.CrossRefGoogle Scholar
  15. Heagerty, P. J., and Y. Zheng. 2005. Survival model predictive accuracy and ROC curves. Biometrics, 61, 92–105.MathSciNetCrossRefGoogle Scholar
  16. Hilsenbeck, S. G., and G. M. Clark. 1996. Practical p-value adjustment for optimally selected cutpoints. Stat. Med., 15, 103–112.CrossRefGoogle Scholar
  17. Kadota, K., C. Colovos, K. Suzuki, N. P. Rizk, M. P. Dunphy, E. C. Zabor, C. S. Sima, A. Yoshizawa, W. D. Travis, V. W. Rusch, and P. S. Adusumilli. 2012. FDG-PET SUVmax Combined with IASLC/ATS/ERS histologic classification improves the prognostic stratification of patients with stage I lung adenocarcinoma. Ann. Surg. Oncol., 19, 3598–3605.CrossRefGoogle Scholar
  18. Kalbfleisch, J. D., and R. L. Prentice. 2002. The statistical analysis of failure time data. New York, NY, Wiley.CrossRefGoogle Scholar
  19. Klein, J. P., and M. L. Moeschberger. 2005. Survival analysis: Techniques for censored and truncated data. New York, NY, Springer.zbMATHGoogle Scholar
  20. Koziol, J. A., and Z. Jia. 2009. The Concordance Index C and the Mann-Whitney Parameter Pr(X < Y) with randomly censored data. Biometrical Journal, 51, 467–474.MathSciNetCrossRefGoogle Scholar
  21. Lausen, B., and M. Schumacher. 1992. Maximally selected rank statistics. Biometrics, 48, 731–785.CrossRefGoogle Scholar
  22. Mazumdar, M., and J.R. Glassman. 2000. Categorizing a prognostic variable: review of methods, code for easy implementation and applications to decision-making about cancer treatments. Stat. Med., 19, 113–132.CrossRefGoogle Scholar
  23. Miller, R., and D. Siegmund. 1982. Maximally selected chi-square statistics. Biometrics, 38, 1011–1016.MathSciNetCrossRefGoogle Scholar
  24. Pepe, M. S., 2003. The statistical evaluation of medical tests for classification and prediction. New York, NY, Oxford University Press.zbMATHGoogle Scholar
  25. Perkins, N. J., and E. F. Schisterman. 2005. The Youden Index and the optimal cutpoint corrected for measurement error. Biometrical Journal, 47, 428–441.MathSciNetCrossRefGoogle Scholar
  26. Perkins, N. J., and E. F. Schisterman. 2006. The inconsistency of “optimal” cutpoints obtained using two criteria based on the receiver operating characteristic curve. American Journal of Epidemiology, 163, 670–675.CrossRefGoogle Scholar
  27. Pratt, J. W., and J. D. Gibbons. 1981. Concepts of nonparametric theory. New York, NY, Springer-Verlag.CrossRefGoogle Scholar
  28. Royston, P., D. G. Altman, and W. Sauerbrei. 2006. Dichotomizing continuous predictors in multiple regression: A bad idea. Stat. Med., 25, 127–141.MathSciNetCrossRefGoogle Scholar
  29. Rubin, D. B. and N. Schenker. 1987. Logit-based interval estimation for binomial data using the Jeffreys prior. Sociolo. Methodol., 17, 131–144.CrossRefGoogle Scholar
  30. Ruopp, M. D., N. J. Perkins, B. W. Whitcomb, and E. F. Schisterman. 2008. Youden Index and optimal cut-point estimated from observations affected by a lower limit of detection. Biometrical J., 50, 419–430.MathSciNetCrossRefGoogle Scholar
  31. Volinsky, C., D. Madigan, A. E. Raftery, and R.A. Kronmal. 1997. Bayesian model averaging in proportional hazard models: Predicting the risk of a stroke. Appl. Stat., 46, 443–448.zbMATHGoogle Scholar
  32. Youden, W. J. 1950. Index for rating diagnostic tests. Cancer, 3, 32–35.CrossRefGoogle Scholar
  33. Wartenberg, D., and M. Northridge. 1991. Defining exposure in case-control studies: A new approach. Am. J. Epidemiol., 133, 1058–1071.CrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2013

Authors and Affiliations

  1. 1.Department of Epidemiology and BiostatisticsMemorial Sloan-Kettering Cancer CenterNew YorkUSA

Personalised recommendations