Journal of Statistical Theory and Practice

, Volume 7, Issue 2, pp 360–380 | Cite as

Testing for a Changepoint in the Cox Survival Regression Model

  • David M. Zucker
  • Sarit Agami
  • Donna SpiegelmanEmail author


The Cox regression model is a popular model for analyzing the relationship between a covariate and a survival endpoint. The standard Cox model assumes that the covariate effect is constant across the entire covariate domain. However, in many epidemiological and other applications, there is interest in considering the possibility that the covariate of main interest is subject to a threshold effect: a change in the slope at a certain point within the covariate domain. In this article, we discuss testing for a threshold effect in the case where the potential threshold value is unknown. We consider a maximum efficiency robust test (MERT) of linear combination form and supremum type tests. We present the relevant theory, present a simulation study comparing the power of various test statistics, and illustrate the use of the tests on data from the Nurses Health Study (NHS) concerning the relationship between chronic exposure to particulate matter of diameter 10 µm or less (PM10) and fatal myocardial infarction. We also discuss power calculation for studies aimed at investigating the presence of a threshold effect, and present an illustrative power calculation. The simulation results suggest that the best overall choice of test statistic is either the full supremum statistic or the three-point supremum type statistic. The power calculation methodology will be useful in study planning. Matlab software for performing the tests and power calculation is available by download from the first author’s website.


Threshold Risk Score test Maximin efficiency robust test Supremum test 

AMS Classification



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abrahamowicz, M., T. Schopflocher, K. Leffondre, R. du Berger, and D. Krewski 2003. Flexible modeling of exposure-response relationship between long-term average levels of particulate air pollution and mortality in the American Cancer Society Study. J. Toxicol. Environ. Health A, 66, 1625–1653.CrossRefGoogle Scholar
  2. Akaike, H. 1974. A new look at the statistical model identification. IEEE Trans. Automatic Control, 19, 716–723.CrossRefMathSciNetzbMATHGoogle Scholar
  3. Andersen, P. K., O. Borgan, R. D. Gill, and N. Keiding 1993. Statistical models based on counting processes. New York, NY, Springer-Verlag.CrossRefzbMATHGoogle Scholar
  4. Andersen, P. K., and R. Gill 1982. Cox’s regression model for counting processes: A large sample study. Ann. Stat., 10, 1100–1120.CrossRefMathSciNetzbMATHGoogle Scholar
  5. Cox, D. R. 1972. Regression models and life tables (with discussion). J. R. Stat. Soc. Ser. B, 34, 187–220.zbMATHGoogle Scholar
  6. Cox, D. R. 1975. Partial likelihood. Biometrika, 62, 269–276.CrossRefMathSciNetzbMATHGoogle Scholar
  7. Cox, D. R., and D. V. Hinkley 1974. Theoretical statistics. London, UK, Chapman and Hall.CrossRefzbMATHGoogle Scholar
  8. Davies, R. B. 1977. Hypothesis testing when a nuisance parameter is present only under the alternative. Biometrika, 64, 247–254.CrossRefMathSciNetzbMATHGoogle Scholar
  9. Davies, R. B. 1987. Hypothesis testing when a nuisance parameter is present only under the alternative. Biometrika, 74, 33–43.MathSciNetzbMATHGoogle Scholar
  10. Daniels, M. J., F. Dominici, J. M. Samet, and S. L. Zeger 2000. Estimating particulate matter-mortality dose-response curves and threshold levels: An analysis of daily time-series for the 20 largest US cities. Am. J. Epidemiol., 152, 397–406.CrossRefGoogle Scholar
  11. Durrelman, S., and R. Simon, 1989. Flexible regression models with cubic splines. Stat. Med., 8, 551–561.CrossRefGoogle Scholar
  12. Feder, P. I. 1975. On asymptotic distribution theory in segmented regression problems—Identified case. Ann. Stat., 3, 49–83.CrossRefMathSciNetzbMATHGoogle Scholar
  13. Fleming, T. R., and D. P. Harrington 1991. Counting processes and survival analysis. Hoboken, NJ, John Wiley and Sons.zbMATHGoogle Scholar
  14. Freidlin, B., M. J. Podgor, and J. L. Gastwirth 1999. Efficiency robust tests for survival or ordered categorical data. Biometrics, 55, 883–886.CrossRefzbMATHGoogle Scholar
  15. Gastwirth, J. L. 1966. On robust procedures. J. Am. Stat. Assoc., 61, 929–948.CrossRefMathSciNetzbMATHGoogle Scholar
  16. Gastwirth, J. L. 1985. The use of maximin efficiency robust tests in combining contingency tables and survival analysis. J. Am. Stat. Assoc., 80, 380–384.CrossRefMathSciNetzbMATHGoogle Scholar
  17. Genz, A., and F. Bretz 1999. Numerical computation of multivariate t-probabilities with application to power calculation of multiple contrasts. J. Stat. Comput. Simulation, 63, 361–378.CrossRefMathSciNetzbMATHGoogle Scholar
  18. Gill, R. D. 1980. Censoring and stochastic integrals. Mathematical Centre Tracts 124, Amsterdam, Matematisch Centrum.zbMATHGoogle Scholar
  19. Goetghebeur, E., and S.J. Pocock 1995. Detection and estimation of J-shaped risk response relationships. J. R. Stat. Soc. Ser. A, 158, 107–121.CrossRefGoogle Scholar
  20. Govindarajulu, U. S., D. Spiegelman, S. W. Thurston, B. Ganguli, and E. A. Eisen 2007. Comparing smoothing techniques in Cox models for exposure-response relationships. Stat. Med., 26, 3735–3752.CrossRefMathSciNetGoogle Scholar
  21. Govindarajulu, U. S., E. J. Malloy, B. Ganguli, D. Spiegelman, and E. A. Eisen 2009. The comparison of alternative smoothing methods for fitting non-linear exposure-response relationships with Cox models in a simulation study. Int. J. Biostat., 5(1), article 2 (electronic journal:
  22. Greenland, S. 1995. Avoiding power loss associated with categorization and ordinal scores in dose-response and trend analysis. Epidemiology, 6, 450–454.CrossRefGoogle Scholar
  23. Hsieh, F. Y., and P. W. Lavori 2000. Sample-size calculations for the Cox proportional hazards regression model with nonbinary covariates. Controlled Clin. Trials, 21, 552–560.CrossRefGoogle Scholar
  24. Julious, S. A. 2001 Inference and estimation in a changepoint regression problem. J. R. Stat. Soc. Ser. D (Statistician), 50, 51–61.CrossRefMathSciNetGoogle Scholar
  25. Kalbfleisch, J. D., and R. L. Prentice 2002. The statistical analysis of failure time data, 2nd ed. Hoboken, NJ, John Wiley and Sons.CrossRefzbMATHGoogle Scholar
  26. Klein, J. P., and M. L. Moeschberger 2003 Survival analysis: techniques for censored and truncated data, 2nd ed. New York, NY, Springer-Verlag.zbMATHGoogle Scholar
  27. Kosorok, M., and R. Song 2007. Inference under right censoring for transformation models with a change-point based on a covariate threshold. Ann. Stat., 35, 957–989.CrossRefMathSciNetzbMATHGoogle Scholar
  28. Küchenhoff, H., and U. Wellisch 1997. Asymptotics for generalized linear segmented regression models with unknown breakpoint. Sonderforschungsbereich, Discussion Paper 83.Google Scholar
  29. Levy, J. I. 2003. Issues and uncertanties in estimating the health benefits of air pollution control. J. Toxicol. Environ. Health A, 66, 1865–1871.CrossRefGoogle Scholar
  30. Liang, K. Y., S. G. Self, and X. Liu 1990. Cox’s proportional hazards model with change point: An epidemiologic application. Biometrics, 46, 783–793.CrossRefGoogle Scholar
  31. Liu, M., W. Lu, and Y. Shao 2008. A Monte Carlo approach for change-point detection in the Cox proportional hazards model. Stat. Med., 27, 3894–3909.CrossRefMathSciNetGoogle Scholar
  32. Muggeo, V. 2003 Estimating regression models with unknown break-points. Statistics in Medicine, 22, 3055–3071.CrossRefGoogle Scholar
  33. Paciorek, C. J., J. D. Yanosky, R. C. Puett, F. Laden, and H. H. Suh 2009. Practical large-scale spatio-temporal modeling of particulate matter concentrations. Ann. Appl. Stat., 3, 370–397.CrossRefMathSciNetzbMATHGoogle Scholar
  34. Pons, O. 2003. Estimation in a Cox regression model with a change-point according to a threshold in a covariate. Ann. Stat., 31, 442–463.CrossRefMathSciNetzbMATHGoogle Scholar
  35. Pope, C. A., 3rd, M. J. Thun, M. M. Namboodiri, D. W. Dockery, J. S. Evans, F. E. Speizer, and C. W. Heath, Jr. 1995. Particulate air pollution as a predictor of mortality in a prospective study of U.S. adults. Am. J. Respir. Crit. Care Med., 151, 669–674.CrossRefGoogle Scholar
  36. Puett, R. C., J. E. Hart, J. D. Yanosky, C. Paciorek, J. Schwartz, H. Suh, F. E. Speizer, and F. Laden 2009. Chronic fine and coarse particulate exposure, mortality, and coronary heart disease in the Nurses’ Health Study. Environ. Health Perspect., 117, 1697–1701.CrossRefGoogle Scholar
  37. Roberts, S., and Martin, M. A. (2006). The question of nonlinearity in the dose-response relation between particulate matter air pollution and mortality: Can akaike’s information criterion be trusted to take the right turn? Am. J. Epidemiol., 164, 1242–1250.CrossRefGoogle Scholar
  38. Samoli, E., A. Analitis, G. Touloumi, J. Schwartz, H. R. Anderson, J. Sunyer, L. Bisanti, D. Zmirou, J. M. Vonk, J. Pekkanen, P. Goodman, A. Paldy, C. Schindler, and K. Katsouyanni 2005. Estimating the exposure-response relationships between particulate matter and mortality within the APHEA multicity project. Environ. Health Perspect., 113, 88–95.CrossRefGoogle Scholar
  39. Schoenfeld, D. 1981. The asymptotic properties of nonparametric tests for comparing survival distributions. Biometrika, 68, 316–319.CrossRefMathSciNetGoogle Scholar
  40. Seber, G. A. F., and C. J. Wild 1989. Nonlinear regression. New York, NY, Wiley.CrossRefGoogle Scholar
  41. Smith, R. L., D. Spitzner, Y. Kim, and M. Fuentes 2000. Threshold dependence of mortality effects for fine and coarse particles in Phoenix, Arizona. J. Air Waste Manage. Assoc., 50, 1367–1379.CrossRefGoogle Scholar
  42. Wu, K., W. C. Willett, C. S. Fuchs, G. A. Colditz, and E. L. Giovannucci 2002. Calcium intake and risk of colon cancer in women and men. J. Nal. Cancer Inst., 94, 437–446.CrossRefGoogle Scholar
  43. Yanosky, J., C. Paciorek, J. Schwartz, F. Laden, R. Puett, and H. Suh 2008. Spatio-temporal modeling of chronic PM10 exposure for the Nurses’ Health Study. Atmos. Environ., 42, 4047–4062.CrossRefGoogle Scholar
  44. Zheng, G., and Z. Chen 2005. Comparison of maximum statistics for hypothesis testing when a nuisance parameter is present only under the alternative. Biometrics, 61, 254–258.CrossRefMathSciNetGoogle Scholar
  45. Zucker, D. M., and S. Yang 2006. Inference for a family of survival models encompassing the proportional hazards and proportional odds models. Stat. in Med., 25, 995–1014.CrossRefMathSciNetGoogle Scholar

Copyright information

© Grace Scientific Publishing 2013

Authors and Affiliations

  • David M. Zucker
    • 1
  • Sarit Agami
    • 1
  • Donna Spiegelman
    • 2
    Email author
  1. 1.Department of StatisticsHebrew UniversityJerusalemIsrael
  2. 2.Departments of Epidemiology and BiostatisticsHarvard School of Public HealthBostonUSA

Personalised recommendations