A1616
Title: Dependent censoring with simultaneous death times
Authors: Mikael Escobar-Bach - University of Angers (France) [presenting]
Salima Helali - UTC, Compiègne (France)
Abstract: The problem of dependent censoring models with positive probability that failure times are equal is considered. A Marshall-Olkin type model is proposed and some properties of the associated survival copula in its application to censored data are studied. Estimators for the marginal distributions and joint survival probabilities under different schemes are introduced and their asymptotic normality is established under appropriate conditions. The finite-sample performance of the approach is evaluated through a simulation study on synthetic data and an application to real data.
