Incorporating Sampling Bias in Analyzing Bivariate Survival Data with Interval Sampling and Application to HIV Research

• Activity Number: 403
• Type: Topic Contributed
• Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Hong Zhu*+ and Mei-Cheng Wang
• Companies: Johns Hopkins Bloomberg School of Public Health and The Johns Hopkins University
• Keywords: Bivariate survival data ; Copula model ; Interval sampling ; Semiparametric estimation ; Stationarity and semi-stationarity

Abstract

In biomedical studies, it is common to collect data with incidence of a disease occurring within a calendar time interval, and bivariate survival data arise and are used as major outcome to identify the progression of a disease. This paper considers an interval sampling scheme, where the first failure event (i.e., HIV infection) is identified within a calender time interval, the occurrence of the initiating event (i.e., birth) can be retrospectively confirmed, and the second failure event (i.e., death) is observed subject to right censoring. The focus is on incorporating sampling bias in analyzing this type of bivariate survival data. In this paper, we develop a copula models method and study the dependency structure of the bivariate survival data. The method is evaluated by simulations and illustrated by Rakai HIV seroconversion data to study the disease progression of HIV infection.