The Annals of Statistics

A generalized additive regression model for survival times

Thomas H. Scheike

Full-text: Open access


We present a non-parametric survival model with two time-scales. The time-scales are equivalent up to a constant that varies over the subjects. Covariate effects are modelled linearly on each time scale by additive Aalen models. Estimators of the cumulative intensities on the two time-scales are suggested by solving approximate local maximum likelihood estimating equations. The local estimating equations necessitate only the choice of one bandwidth. The estimators are provided with large sample properties. The model is applied to data on patients with myocardial infarction, and used to describe the prognostic effect of covariates on the two time scales, time since myocardial infarction and age.

Article information

Ann. Statist. Volume 29, Number 5 (2001), 1344-1360.

First available in Project Euclid: 8 February 2002

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62N01: Censored data models
Secondary: 62N02: Estimation 62G20: Asymptotic properties

Additive Aalen model counting process disability model illness-death model generalized additive models multiple time-scales non-parametric estimation survival data varying-coefficient models


Scheike, Thomas H. A generalized additive regression model for survival times. Ann. Statist. 29 (2001), no. 5, 1344--1360. doi:10.1214/aos/1013203457.

Export citation


  • Aalen, O. O. (1980). A model for non-parametric regression analysis of counting processes. Lecture Notes in Statist. 2 1-25. Springer, New York.
  • Aalen, O. O. (1989). A linear regression model for the analysis of life times. Statistics in Medicine 8 907-925.
  • Aalen, O. O. (1993). Further results on the non-parametric linear regression model in survival analysis. Statistics in Medicine 12 1569-1588.
  • Andersen, P. K., Borgan, Ø., Gill, R. D. and Keiding, N. (1993). Statistical Models Based on Counting Processes. Springer, New York.
  • Hastie, T. and Tibshirani, R. (1986). Generalized additive models. J. Amer. Statist. Assoc. 81 297-318.
  • Hastie, T. and Tibshirani, R. (1993). Varying-coefficient models. J. Roy. Statist. Soc. Ser. B 55 757-796.
  • Huang, J. (1999). Efficient estimation of the partly linear additive Cox model. Ann. Statist. 27 1536-1563.
  • Huffer, F. W. and McKeague, I. W. (1991). Weighted least squares estimation for Aalen's additive risk model. J. Amer. Statist. Assoc. 86 114-129.
  • Keiding, N. (1991). Age-specific incidence and prevalence: A statistical perspective (withdiscussion). J. Roy. Statist. Soc. Ser. A 154 371-396.
  • Kooperberg, C., Stone, C. and Truong, Y. (1991). The L2 rate of convergence for hazard regression. Scand. J. Statist. 22 143-158.
  • Li, G. and Doss, H. (1995). An approachto nonparametric regression for life history data using local linear fitting. Ann. Statist. 23 787-823.
  • Linton, O., Nielsen, J. P. and Van de Geer, S. (1999). Estimating multiplicative and additive marker dependent hazard functions by backfitting with the assistance of marginal integration. Technical Report 7, Dept. Statistics, Univ. Copenhagen.
  • McKeague, I. W. (1988). Asymptotic theory for weighted least squares estimators in Aalen's additive risk model. Contemp. Math. 80 139-152.
  • McKeague, I. W. and Sasieni, P. D. (1994). A partly parametric additive risk model. Biometrika 81 501-514.
  • Nielsen, J. P. (1999). Super efficient hazard estimation. Biometrika 86 227-232.
  • Oakes, D. (1995). Multiple time scales in survival analysis. Lifetime Data Anal. 1 7-18. Ramlau-Hansen, H., Jespersen, N. C. B., Andersen, P., Borch-Johnsen, K. and Deckert, T.
  • (1987). Life insurance for insulin-dependent diabetics. Scand. Actuar. J. 19-36.