Statistical analysis of bivariate interval-censored failure time data

Abstract

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Interval-censored failure time data arise when the failure time of interest in a survival study is not exactly observed but known only to fall within some interval. One area that often produces such data is medical studies with periodic follow-ups, in which the medical condition of interest such as the onset of a disease is only known to occur between two adjacent examination times. An important special case of intervalcensored data is current status data which arise when each study subject is observed only once and the only information available is whether the failure event of interest has occurred or not by the observation time. The areas that often yield such data include tumorigenicity experiments and cross-sectional studies. Sometimes we refer to current status data as case I interval-censored data, and the general case as case II interval-censored data. The analysis of both case I and case II interval-censored data has recently attracted a great deal of attention and many procedures have been proposed for various issues related to it. However, there are still a number of problems that remain unsolved or lack approaches that are simpler, more efficient and apply to more general situations compared to the existing ones. This is especially the case for multivariate intervalcensored data which arise if there are multiple failure times of interest and all of them suffer intervalcensoring. This dissertation focuses on the statistical analysis for bivariate interval-censored data, including regression analysis, model selection and estimation of the association between failure times.

Assessment of Cumulative Incidence and Severity of Primary Open-Angle Glaucoma Among Participants in the Ocular Hypertension Treatment Study After 20 Years of Follow-up

“…Kaplan-Meier product limit methods with interval censoring time were used to estimate the 20-year incidence of POAG. 10 Statistical analysis was performed using SAS software, version 9.4 (SAS Institute Inc) and the R survfit package, version 2.11-4 (R Foundation for Statistical Computing). The significance threshold was P < .05.…”

Ordered and censored lifetime data in reliability: An illustrative review

“…In general, one may apply different interval censoring to each individual so that the thresholds τ i used in Equation () may be different for each measurement. For details, we refer to Nelson (1982), Huang and Wellner (1997), Lawless (2003), Sun (2006), Gerds and Meier‐Hirmer (2014), and Bogaerts et al (2017). For simplicity, we assume an iid model as in Equation () as well as the same observation intervals for all individuals.…”

Two‐phase designs with current status data

“…Current status data arise in time‐to‐event studies when failure status is only determined at a single assessment time resulting in either right‐ or left‐censored observations 1,2 . Such data are often encountered in sociology, demography, epidemiology, and medical research.…”

“…In biomedical research, examples include orthopedic surgery trials where blood samples are drawn upon hospital discharge to assess immunological response to antithrombotic therapy, 3 ophthalmology where interest lies in the time to calcification of implanted lens following cataract surgery, 4 partner studies in research on risk of HIV transmission, 5 and developmental studies of the age of menarche 6 . Statistical methods for parametric and semiparametric regression analysis involving current status data are described in Sun, 2 and Jewell and van der Laan 7 discuss how to gain insights into more complex processes under current status observation schemes.…”