Westerman, R.; Reese, J. P.; Mueller, U. O. (2013)
JSM Proceedings, Biometric Sections, Alexandria, VA: American Statistical Association: 1140–1148
In terms of competing risks Long-term Mixture Survival Models are widely used for the analysis of individuals who may never experience the considered type of failure. If we add the possibility of a lasting therapy success. some individuals have to be treated as immune to a specific cause of failure or to be defined as long-term survivors. In case of multi- or bivariate cause-specific survival data different dependence structures can be modeled with different copula functions. There are two main methodical goals for modeling marginal distributions to be considered: First flexibility and second masked causes. We propose a Bivariate Mixture Long-term Survival model based on the Farlie-Gumbel-Morgenstern (FGM) copula. Data simulations will be provided with SEER Breast Cancer Data.