Modeling the Bivariate time to Mortality from HIV-l

Abstract

Frailty models are used in survival analysis to account for unobserved heterogeneity in individual risks to disease and death. Heterogeneity induces deviations in an individual's risk of an event as well as associations between survival times. A bivariate frailty model characterizes the heterogeneity. The aim of this project is to model the bivariate time to mortality and determine factors associated with it. The data used is on related survival times of 476 mother-baby pairs in a two-year follow up study with several covariates such as infection status of babies, breast feeding, CD4 count and viral load. During the study follow-up 124 deaths (95 infants and 29 mothers) occurred. Key words: bivariate frailty, heterogeneity and mortality.