The Poisson Generalized Birnbaum-Saunders Cure Model and Application in Breast Cancer Data

Abstract

The cure rate survival models are generally used to model lifetime data with long term survivors. We assumes the number of competing causes of the event of interest has the Poisson distribution and the time to the event of interest follows the Generalized Birnbaum-Saunders distribution. The Poisson GB-S distribution has been defined and useful representations for its density function have been presented which facilitates obtaining some mathematical properties. The parameters of the model with cure rate have been estimated using the maximum likelihood method. For different sample sizes and censoring percentages, several simulations have been performed and a real data set from the medical area has been analyzed.