Biometrika Advance Access originally published online on August 5, 2007
Biometrika 2007 94(3):719-733; doi:10.1093/biomet/asm058
Copyright © 2007 Biometrika Trust
Articles |
Survival analysis with temporal covariate effects
Department of Biostatistics, Emory University, Atlanta, Georgia 30322, U.S.A.
lpeng{at}sph.emory.edu
yhuang5{at}sph.emory.edu
Received for publication 1 March 2006. Revision received 1 February 2007.
We propose a natural generalization of the Cox regression model, in which the regression coefficients have direct interpretations as temporal covariate effects on the survival function. Under the conditionally independent censoring mechanism, we develop a smoothing-free estimation procedure with a set of martingale-based equations. Our estimator is shown to be uniformly consistent and to converge weakly to a Gaussian process. A simple resampling method is proposed for approximating the limiting distribution of the estimated coefficients. Second-stage inferences with time-varying coefficients are developed accordingly. Simulations and a real example illustrate the practical utility of the proposed method. Finally, we extend this proposal of temporal covariate effects to the general class of linear transformation models and also establish a connection with the additive hazards model.
Key Words: Censoring • Cox regression • Gaussian process • Linear transformation model • Martingale • Time-varying coefficient
References
-
Aalen O. O. Lecture Notes in Statistics (1980) Vol. 3. New York: Springer-Verlag. 1–25. A model for nonparametric regression analysis of counting processes.
Andersen P. K., Borgan Ø., Gill R. D., Keiding N. Statistical Models Based on Counting Processes (1998) 2nd ed. New York: Springer-Verlag.
Andersen P. K., Gill R. D. Cox's regression model for counting processes: A large sample study. Ann. Statist. (1982) 10:1100–20.[CrossRef]
Bennett S. Analysis of survival data by the proportional odds model. Statist. Med. (1983) 2:273–7.[CrossRef]
Cai Z., Sun Y. Local linear estimation for time-dependent coefficients in Cox's regression models. Scand. J. Statist. (2003) 30:93–111.[CrossRef]
Chen K., Jin Z., Ying Z. Semiparametric analysis of transformation models with censored data. Biometrika (2002) 89:659–68.
Cheng S. C., Wei L. J., Ying Z. Analysis of transformation models with censored data. Biometrika (1995) 82:835–45.
Cox D. R. Regression models and life-tables (with Discussion). J. R. Statist. Soc. (1972) B 34:187–220.
Fine J. P., Yan J., Kosorok M. R. Temporal process regression. Biometrika (2004) 91:683–703.
Fleming T., Harrington D. Counting Processes and Survival Analysis (1991) New York: Wiley.
Fygenson M., Ritov Y. Monotone estimating equations for censored data. Ann. Statist. (1994) 22:732–46.[CrossRef]
Gill R. D., Johansen S. A survey of product-integration with a view toward application in survival analysis. Ann. Statist. (1990) 18:1501–55.[CrossRef]
Griffel D. H. Applied Functional Analysis (1981) 2nd ed. New York: Halsted Press.
Huffer F. W., McKeague I. W. Weighted least squares estimation for Aalen's additive risk model. J. Am. Statist. Assoc. (1991) 86:114–29.[CrossRef][Web of Science]
Jung S. Regression analysis for long-term survival rate. Biometrika (1996) 83:227–32.
Kalbfleisch J. D., Prentice R. L. The Statistical Analysis of Failure Time Data (2002) 2nd ed. New York: Wiley.
Lin D. Y., Fleming T. R., Wei L. J. Confidence bands for survival curves under the proportional hazards model. Biometrika (1994) 81:73–81.
Lin D. Y., Wei L. J., Ying Z. Checking the Cox model with cumulative sums of martingale-based residuals. Biometrika (1993) 80:557–72.
Lin D. Y., Ying Z. Semiparametric analysis of the additive risk model. Biometrika (1994) 81:61–71.
Lu W. Marginal regression of multivariate event times based on linear transformation models. Lifetime Data Anal. (2005) 11:389–404.[CrossRef][Web of Science][Medline]
Martinussen T., Scheike T. H. A flexible additive multiplicative hazard model. Biometrika (2002) 89:283–98.
Martinussen T., Scheike T. H., Skovgaard I. M. Efficient estimation of fixed and time-varying covariate effects in multiplicative intensity models. Scand. J. Statist. (2002) 29:57–74.[CrossRef]
McKeague I. W., Sasieni P. D. A partly parametric additive risk model. Biometrika (1994) 81:501–14.
Murphy S. A., Sen P. K. Time-dependent coefficients in Cox-type regression model. Stoch. Proces. Applic. (1991) 39:153–80.[CrossRef]
Pettitt A. N. Proportional odds model for survival data and estimates using ranks. Appl. Statist. (1984) 33:169–75.[CrossRef]
Prentice R. L. Exponential survivals with censoring and explanatory variables. Biometrika (1973) 60:279–88.
Reinhard H. Differential Equations: Foundations and Applications (1987) New York: Macmillan.
Römisch W. Encyclopedia of Statistical Sciences (2005) Vol. 3, 2nd ed. New York: Wiley. 1575–83. Delta Method, infinite dimensional.
Tian L., Zucker D., Wei L. J. On the Cox model with time-varying regression coefficients. J. Am. Statist. Assoc. (2005) 100:172–83.[CrossRef][Web of Science]
Valsecchi M., Silvestri D., Sasieni P. Evaluation of long-term survival: use of diagnostics and robust estimators with Cox's proportional hazards model. Statist. Med. (1996) 15:2763–80.[CrossRef]
van Der Vaart A. W., Wellner J. A. Weak Convergence and Empirical Processes: With Applications to Statistics (1996) New York: Springer-Verlag.
Verweij P. J. M., van Houwelingen H. C. Time-dependent effects of fixed covariates in Cox regression. Biometrics (1995) 51:1550–6.[CrossRef][Web of Science][Medline]
Winnett A., Sasieni P. Iterated residuals and time-varying covariate effect in Cox regression. J. R. Statist. Soc. (2003) B 65:473–88.[CrossRef]
Yan J., Fine J. P. Functional association models for multivariate survival processes. J. Am. Statist. Assoc. (2005) 100:184–96.[CrossRef][Web of Science]
Zucker D. M., Karr A. F. Nonparametric survival analysis with time-dependent effects: a penalized partial likelihood approach. Ann. Statist. (1990) 18:329–53.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||||