Abstract
A popular model for competing risks postulates the existence of a latent unobserved failure time for each risk. Assuming that these underlying failure times are independent is attractive since it allows standard statistical tools for right-censored lifetime data to be used in the analysis. This paper proposes simple independence score tests for the validity of this assumption when parametric regression models are used to model the individual risks. The score tests are derived for the alternatives that specify that copulas are responsible for a possible dependency between competing risks. The test statistics are functions of the Cox and Snell residuals. A variance estimator is derived by writing the score function and the Fisher information matrix for the marginal models as stochastic integrals. A simulation study and a numerical example illustrate the methodology proposed in this paper.
Similar content being viewed by others
References
Allison PD (1995) Survival analysis using the SAS system: a practical guide. SAS Institute, Cary
Aly E-EAA, Kochar SC, McKeague IW (1994) Some tests for comparing cumulative incidence functions and cause-specific hazard rates. J Am Stat Assoc 89(427):994–999
Andersen PK, Borgan O, Gill RD, Keiding N (1993) Statistical models based on counting processes. Springer, New York
Bienen HS, van de Walle N (1991) Of time and power. Stanford University Press, Stanford
Carling K, Jacobson T (1995) Modeling unemployment duration in a dependent competing risks framework: identification and estimation. Lifetime Data Anal 1:111–122
Clayton DG (1978) A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika 65:141–152
Crowder M (2001) Classical competing risks. Chapman & Hall/CRC Press, London
Faraggi D, Korn EL (1996) Competing risks with frailty models when treatment affects only one failure type. Biometrika 83(2):467–471
Fermanian JD (2003) Nonparametric estimation of competing risks models with covariates. J Multivar Anal 85:156–191
Fleming TR, Harrington DP (1991) Counting processes and survival analysis. Wiley, New York
Gasbarra D, Karia SR (2000) Analysis of competing risks by using Bayesian smoothing. Scand J Stat 27(4):605–617
Genest C, Ghoudi K, Rivest L-P (1998) Comment on the paper by EW Valdez entitled “Understanding relationships using copulas”. North Am Actuar J 2:143–149
Heckman JJ, Honoré BE (1989) The identifiability of the competing risks model. Biometrika 76(2):325–330
Kwan PH, Singh H (2001) On nonparametric estimation of the survival function with competing risks. Scand J Stat 28:715–724
Luo X, Turnbull BW (1999) Comparing two treatments with multiple competing risks endpoints. Stat Sin 9:985–998
Nelsen R (1999) An introduction to copula. Lecture notes in statistics, vol 139. Springer, New York
Oakes D, Wang A (2003) Copula model generated by Dabrowska’s association measure. Biometrika 90(2):478–4813
Prentice RL, Kalbfleisch JD, Peterson JAV, Flournoy N, Farewell VT, Breslow NE (1978) The analysis of failure times in the presence of competing risks. Biometrics 34(4):541–554
Rivest L-P, Wells MT (2001) A martingale approach to the copula-graphic estimator for the survival function under dependent censoring. J Multivar Anal 79(1):138–155
Saïd M (2004) Méthodes statistiques pour tester la dépendance entre les variables latentes pour des risques concurrents. PhD thesis, Département de Mathématiques et de Statistique, Université Laval
Saïd M, Ghazzali N, Rivest L-P (2003) Score test for dependent censoring with survival data. In: Moore M, Froda S, Léger C (eds) Mathematical statistics and applications: Festschrift for Constance van Eeden, vol 42. Institute of Mathematical Statistics, Hayward, pp 435–462
Slud E, Byar D (1988) How dependent causes of death can make risk factors appear protective. Biometrics 44(1):265–269
Tsiatis A (1975) A nonidentifiability aspect of the problem of competing risks. Proc Nat Acad Sci United States Am 72(1):20–22
Zheng M, Klein JP (1995) Estimates of marginal survival for dependent competing risks based on an assumed copula. Biometrika 82:127–138
Zheng M, Klein JP (1996) Identifiability and estimation of marginal survival functions for dependent competing risks assuming the copula is known. In: Jewell NP, Kimber AC, Lee M-LT, Whitmore GA (eds) Lifetime data models in reliability and survival analysis. Kluwer Academic, Dordrecht, pp 401–408
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Saïd, M., Ghazzali, N. & Rivest, LP. Score tests for independence in parametric competing risks models. TEST 16, 547–564 (2007). https://doi.org/10.1007/s11749-006-0019-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11749-006-0019-5