Statistical analysis of clustered or multivariate interval-censored failure time data
Abstract
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Interval-censored failure time data are a type of the failure time data that often occur in clinical trials with periodic follow-ups among others. In this case, the failure time of interest cannot be observed exactly, but is known to be greater than the last observation time at which the failure has not occurred and less than or equal to the first observation time at which the failure has been observed to occur. Current status data are a special case of interval-censored data that we sometimes refer to it as the case I interval censored data. This type of censoring means that each subject is observed only once for the status of occurrence of the failure of interest, so the survival time is either left- or right-censored. Chapter 4 considers the same problem as that in Chapter 3. There are multivariate current status data with informative censoring. We propose to use the vine-copulas to describe the dependence among the failure times of interest and the censoring time. The proposed estimators are shown to be strongly consistent and the asymptotic normality and efficiency of the regression parameter estimator are established. To assess the finite sample performance of the presented methodology, an extensive simulation study is performed and suggests that the method works well in practical situations. Finally, the proposed approach is applied to a tumorigenicity experiment. Several directions for future research are discussed in Chapter 5.
Degree
Ph. D.
Thesis Department
Rights
Access is limited to the campuses of the University of Missouri.