Dynamic path analysis for event time data: large sample properties and inference

We consider the situation with a survival or more generally a counting process endpoint for which we wish to investigate the effect of an initial treatment. Besides the treatment indicator we also have information about a time-varying covariate that may be of importance for the survival endpoint. The treatment may possibly influence both the endpoint and the time-varying covariate, and the concern is whether or not one should correct for the effect of the dynamic covariate. Recently Fosen et al. (Biometrical J 48:381–398, 2006a) investigated this situation using the notion of dynamic path analysis and showed under the Aalen additive hazards model that the total effect of the treatment indicator can be decomposed as a sum of what they termed a direct and an indirect effect. In this paper, we give large sample properties of the estimator of the cumulative indirect effect that may be used to draw inferences. Small sample properties are investigated by Monte Carlo simulation and two applications are provided for illustration. We also consider the Cox model in the situation with recurrent events data and show that a similar decomposition of the total effect into a sum of direct and indirect effects holds under certain assumptions.

[1]  Z. Ying,et al.  Checking the Cox model with cumulative sums of martingale-based residuals , 1993 .

[2]  Odd O Aalen,et al.  Dynamic Analysis of Recurrent Event Data Using the Additive Hazard Model , 2006, Biometrical journal. Biometrische Zeitschrift.

[3]  C. R. Rao,et al.  Linear Statistical Inference and its Applications , 1968 .

[4]  Judea Pearl,et al.  Direct and Indirect Effects , 2001, UAI.

[5]  O. Aalen.  A linear regression model for the analysis of life times. , 1989, Statistics in medicine.

[6]  O. Aalen,et al.  Further results on the non-parametric linear regression model in survival analysis. , 1993, Statistics in medicine.

[7]  Thomas H Scheike,et al.  The Additive Nonparametric and Semiparametric Aalen Model as the Rate Function for a Counting Process , 2002, Lifetime data analysis.

[8]  N Tygstrup,et al.  Prognostic Factors in Cirrhosis Identified by Cox's Regression Model , 2007, Hepatology.

[9]  The Manton-Woodbury model for longitudinal data with dropouts. , 1997, Statistics in medicine.

[10]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data: Kalbfleisch/The Statistical , 2002 .

[11]  Odd Aalen,et al.  A Model for Nonparametric Regression Analysis of Counting Processes , 1980 .

[12]  J. Robins,et al.  Identifiability and Exchangeability for Direct and Indirect Effects , 1992, Epidemiology.

[13]  D. Cox.  Regression Models and Life-Tables , 1972 .

[14]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data , 1980 .

[15]  S. Wright.  The Method of Path Coefficients , 1934 .

[16]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .

[17]  Danyu Lin,et al.  Marginal Regression Models for Multivariate Failure Time Data , 1998 .

[18]  Torben Martinussen,et al.  A semiparametric additive regression model for longitudinal data , 1999 .

[19]  O. Aalen,et al.  Dynamic path analysis—a new approach to analyzing time-dependent covariates , 2006, Lifetime data analysis.

[20]  S. Cole,et al.  Fallibility in estimating direct effects. , 2002, International journal of epidemiology.

[21]  John D. Kalbfleisch,et al.  Misspecified proportional hazard models , 1986 .

[22]  J. Vaupel,et al.  Exceptional longevity does not result in excessive levels of disability , 2008, Proceedings of the National Academy of Sciences.

[23]  Zhiliang Ying,et al.  Semiparametric regression for the mean and rate functions of recurrent events , 2000 .

[24]  Els Goetghebeur,et al.  Estimation of controlled direct effects , 2008 .