Article first published online: 2 AUG 2013
Copyright © 2013 John Wiley & Sons, Ltd.
Statistics in Medicine
Volume 33, Issue 1, pages 46–58, 15 January 2014
How to Cite
Su, P.-F. and Chi, Y. (2014), Marginal regression approach for additive hazards models with clustered current status data. Statist. Med., 33: 46–58. doi: 10.1002/sim.5914
- Issue published online: 10 DEC 2013
- Article first published online: 2 AUG 2013
- Manuscript Accepted: 17 JUN 2013
- Manuscript Received: 3 FEB 2012
- additive hazards model;
- clustered current status data;
- counting process;
- estimating function;
- marginal regression approach
Current status data arise naturally from tumorigenicity experiments, epidemiology studies, biomedicine, econometrics and demographic and sociology studies. Moreover, clustered current status data may occur with animals from the same litter in tumorigenicity experiments or with subjects from the same family in epidemiology studies. Because the only information extracted from current status data is whether the survival times are before or after the monitoring or censoring times, the nonparametric maximum likelihood estimator of survival function converges at a rate of n1∕3 to a complicated limiting distribution. Hence, semiparametric regression models such as the additive hazards model have been extended for independent current status data to derive the test statistics, whose distributions converge at a rate of n1∕2, for testing the regression parameters. However, a straightforward application of these statistical methods to clustered current status data is not appropriate because intracluster correlation needs to be taken into account. Therefore, this paper proposes two estimating functions for estimating the parameters in the additive hazards model for clustered current status data. The comparative results from simulation studies are presented, and the application of the proposed estimating functions to one real data set is illustrated. Copyright © 2013 John Wiley & Sons, Ltd.