Regression models for survival data with time-dependent covariates are considered. We review estimation in the Cox regression model and discuss problems in connection with data requirements for the analysis, with interpretation of results and with prediction based on such a model. In particular, we discuss how the latter problems may be approached within an extended (Markov process) model. A clinical trial in liver cirrhosis is used for illustration.
Get full access to this article
View all access options for this article.
References
1.
Andersen PKSurvival analysis 1982-1991: The second decade of the proportional hazards regression model. Statistics in Medicine1991 ; 10: 1931-41.
2.
Fleming TR, Harrington DPCounting processes and survival analysis. New York : Wiley, 1991.
3.
Andersen PK, Borgan Ø., Gill RD, Keiding N.Statistical models based on counting processes. New York . Springer, 1992 (in press).
4.
Cox DRRegression models and life-tables (with discussion). Journal of the Royal Statistical Society, Series B1972; 34: 187-220.
5.
Kalbfleisch JD, Prentice RLThe statistical analysis of failure time data. New York : Wiley, 1980.
6.
Lawless JFStatistical models and methods for lifetime data. New York : Wiley, 1982.
Tsiatis AAA large sample study of Cox's regression model. Annals of Statistics1981; 9: 93-108.
9.
Naes T.The asymptotic distribution of the estimator for the regression parameter in Cox's regression model. Scandinavian Journal of Statistics1982; 9: 107-15.
10.
Andersen PK , Gill RDCox's regression model for counting processes: A large sample study. Annals of Statistics1982; 10: 1100-20.
11.
Bailey KRThe asymptotic joint distribution of regression and survival parameter estimates in the Cox regression model. Annals of Statistics1983; 11: 39-58.
12.
Gill RDUnderstanding Cox's regression model: a martingale approach. Journal of theAmerican Statistical Association1984 ; 79: 441-47.
13.
Andersen PK , Borgan Ø.Counting process models for life history data: a review (with discussion). Scandinavian Journal of Statistics1985; 12: 97-158.
14.
Copenhagen Study Group for Liver Disease.Sex, ascites and alcoholism in survival of patients with cirrhosis. Effect of prednisone. New England Journal of Medicine1974; 291: 271-73.
15.
Schlichting P., Christensen E., Andersen PK, Fauerholdt L., Juhl E., Poulsen H., Tygstrup N. for The Copenhagen Study Group for Liver Diseases.Identification of prognostic factors in cirrhosis using Cox's regression model. Hepatology1983; 3: 889-95.
16.
Christensen E., Schlichting P., Andersen PK, Fauerholdt L., Juhl E., Poulsen H., Tygstrup N. for The Copenhagen Study Group for Liver Diseases.A therapeutic index that predicts the individual effects of prednisone in patients with cirrhosis. Gastroenterology1985; 88: 156-65.
17.
Christensen E., Schlichting P., Andersen PK, Fauerholdt L., Schou G., Pedersen BV, Juhl E., Poulsen H., Tygstrup N. for The Copenhagen Study Group for Liver Diseases.Updating prognosis and therapeutic effect evaluation in cirrhosis using Cox's multiple regression model for time dependent variables. Scandinavian Journal of Gastroenterology1986; 21: 163-74.
18.
Thomas DCAddendum to: Methods of cohort analysis: appraisal by application to asbestos mining. By Liddell FDK, McDonald JC, Thomas DC. Journal of the Royal Statistical Society, Series A1977; 140: 469-91.
19.
Oakes D.Survival times: aspects of partial likelihood (with discussion). International Statistical Review1981; 49: 235-64.
20.
Prentice RLOn the design of synthetic case-control studies . Biometrics1986; 42: 301-10.
21.
Goldstein L. , Langholz B.Asymptotic theory for nested case-control sampling in the Cox regression model. Annals of Statistics1992 (in press).
22.
Borgan Ø. , Goldstein L., Langholz B.Generalized nested case-control sampling in Cox's regression model: a marked point process approach. Statistical Research Report 1/92, Institute of Mathematics, University of Oslo : 1992.
23.
Prentice RLA case-cohort design for epidemiologic cohort studies and disease prevention trials. Biometrika1986; 73: 1-11.
24.
Self SG, Prentice RLAsymptotic distribution theory and efficiency results for case-cohort studies . Annals of Statistics1988; 16: 64-81.
25.
Andersen PKTime-dependent covariates and Markov processes. In: Moolgavkar SH, Prentice RL (eds.) Modern statistical methods in chronic disease epidemiology , 82-103, New York: John Wiley and Sons, 1986 .
26.
Prentice RL , Williams BJ, Peterson AVOn the regression analysis of multivariate failure time data. Biometrics1981; 68: 373-79.
27.
Aalen OO, Johansen S.An empirical transition matrix for nonhomogeneous Markov chains based on censored observations. Scandinavian Journal of Statistics1978; 5: 141-50.
28.
Andersen PK , Hansen LS, Keiding N.Non- and semiparametric estimation of transition probabilities from censored observations of a non-homogeneous Markov process . Scandinavian Journal of Statistics1991; 18: 153-67.
29.
Chiang CLIntroduction to stochastic processes in biostatistics. New York: Wiley, 1968.
30.
Kay R.A.Markov model for analysing cancer markers and disease states in survival models . Biometrics1986; 42: 855-65.
31.
Andersen PK , Hansen LS, and Keiding N.Assessing the influence of reversible disease indicators on survival. Statistics in Medicine1991; 10: 1061-7.
32.
Aalen OOA model for non-parametric regression analysis of counting processes . Springer Lecture Notes in Statistics1980 ; 2: 1-25.
33.
Aalen OOA linear regression model for the analysis of life times. Statistics in Medicine1989; 8: 907-25.
34.
McKeague IW , and Utikal KJInference for a nonlinear counting process regression model. Annals of Statistics1990 ; 18: 1172-87.
35.
McKeague IW , and Utikal KJGoodness-of-fit tests for additive hazards and proportional hazards models. Scandinavian Journal of Statistics1991; 18177-95.
36.
Diggle PJAn approach to the analysis of repeated measurements. Biometrics1988; 44: 959-71.
37.
Diggle PJTesting for random dropouts in repeated measurement data. Biometrics1989; 45: 1255-58.
38.
Prentice RL , Gloeckler LARegression analysis of grouped survival data with application to breast cancer data. Biometrics1978;34:57-67.
