Lifetime Data Analysis

, Volume 8, Issue 1, pp 21–34 | Cite as

Validation of A Heteroscedastic Hazards Regression Model

  • Hong-Dar Isaac Wu
  • Fushing Hsieh
  • Chen-Hsin Chen


A Cox-type regression model accommodating heteroscedasticity, with a power factor of the baseline cumulative hazard, is investigated for analyzing data with crossing hazards behavior. Since the approach of partial likelihood cannot eliminate the baseline hazard, an overidentified estimating equation (OEE) approach is introduced in the estimation procedure. Its by-product, a model checking statistic, is presented to test for the overall adequacy of the heteroscedastic model. Further, under the heteroscedastic model setting, we propose two statistics to test the proportional hazards assumption. Implementation of this model is illustrated in a data analysis of a cancer clinical trial.

heteroscedasticity Cox model proportional hazards crossing hazards 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. O. O. Aalen, “Heterogeneity in survival analysis,” Statistics in Medicine vol. 7 pp. 1121–1137, 1988.Google Scholar
  2. P. K. Andersen, Ø Borgan, R. D. Gill and N. Keiding, Statistical Models Based on Counting Processes, Springer-Verlag: New York, 1993.Google Scholar
  3. N. E. Breslow, L. Edler and J. Berger, “A two-sample censored-data rank test for acceleration,” Biometrics vol. 40 pp. 1049–1062, 1984.Google Scholar
  4. D. R. Cox, “Regression models and life-tables (with discussion),” Journal of the Royal Statistical Society, Series B vol. 34 pp. 187–220, 1972.Google Scholar
  5. T. R. Fleming, J. R. O'Fallon, P. C. O'Brien, and D. P. Harrington, “Modified Kolmogorov-Smirnov test procedures with application to arbitrarily right-censored data,” Biometrics vol. 36 pp. 607–625, 1980.Google Scholar
  6. M. H. Gail, S. Wieand, and S. Piantadosi, “Biased estimates of treatment effect in randomized experiments with nonlinear regression and omitted covariates,” Biometrika vol. 71 pp. 431–444, 1984.Google Scholar
  7. S. Geman and C.-R. Hwang, “Nonparametric maximum likelihood estimation by the method of sieves,” The Annals of Statistics vol. 10 pp. 401–414, 1982.Google Scholar
  8. R. D. Gill and M. Schumacher, “A simple test of the proportional hazards assumption,” Biometrika vol. 74 pp. 289–300, 1987.Google Scholar
  9. P. Hougaard, “Life table method for heterogeneous populations: distributions describing the heterogeneity,” Biometrika vol. 71 pp. 75–83, 1984.Google Scholar
  10. P. Hougaard, “Survival models for heterogeneous populations derived from stable distributions,” Biometrika vol. 73 pp. 387–396, 1986.Google Scholar
  11. F. Hsieh, “The empirical process approach for semiparametric two-sample models with heterogeneous treatment effect,” Journal of the Royal Statistical Society, Series B vol. 57 pp. 735–748, 1995.Google Scholar
  12. F. Hsieh, “A transformation model for two survival curves: an empirical process approach,” Biometrika vol. 83 pp. 519–528, 1996.Google Scholar
  13. F. Hsieh, “On heteroscedastic hazards Regression models: theory and application,” Journal of the Royal Statistical Society, Series B vol. 63 (to appear), 2001.Google Scholar
  14. D. Y. Lin, “Goodness of fit for the Cox regression model based on a class of parameter estimators,” Journal of The American Statistical Association vol. 86 pp. 725–728, 1991.Google Scholar
  15. T. Moreau, J. O'Quigley, and M. Mesbah, “A global goodness-of-fit statistic for the proportional hazards model,” Applied Statistics vol. 34 pp. 212–218, 1985.Google Scholar
  16. T. Moreau, J. Maccario, J. Lellouch, and C. Huber, “Weighted log rank statistics for comparing two distributions,” Biometrika vol. 79 pp. 195–198, 1992.Google Scholar
  17. J. O'Quigley, “On a two-sided test for crossing hazards,” The Statistician vol. 43 pp. 563–569, 1994.Google Scholar
  18. C. Quantin, T. Moreau, B. Asselain, T. Maccario, and J. Lellouch, “A regression survival model for testing the proportional hazards hypothesis,” Biometrics vol. 52 pp. 874–885, 1996.Google Scholar
  19. D. Schoenfeld, “Chi-squared goodness-of-fit tests for the proportional hazards regression model,” Biometrika vol. 67 pp. 145–153, 1980.Google Scholar
  20. D. M. Stablein and I. A. Koutrouvelis, “A two-sample test sensitive to crossing hazards in uncensored and singly censored data,” Biometrics vol. 41 pp. 643–652, 1985.Google Scholar
  21. P. Tubert-Bitter, A. Kramar, J. J. Chalé, and T. Moreau, “Linear rank tests for comparing survival in two groups with crossing hazards,” Computational Statistics and Data Analysis vol. 18 pp. 547–559, 1994.Google Scholar
  22. L. J. Wei, “Testing goodness-of-fit for the proportional hazards model with censored observations,” Journal of The American Statistical Association vol. 79 pp. 649–652, 1984.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Hong-Dar Isaac Wu
    • 1
  • Fushing Hsieh
    • 2
  • Chen-Hsin Chen
    • 1
  1. 1.School of Public HealthChina Medical CollegeTaichungTaiwan
  2. 2.Institute of Statistical ScienceAcademia SinicaTaipeiTaiwan

Personalised recommendations