Modelos de sobrevivência induzidos por fragilidade discreta série de potência zero-modificada

Abstract

Survival models with a frailty term are presented as an extension of Cox's proportional risk model (COX, 1972), in which a random effect, called frailty, is introduced in the risk function in a multiplicative way with the aim of modeling the unobserved heterogeneity from the units under study. The distribution for the frailty variable is assumed to be continuous and not negative. However, there are some situations it is appropriate to consider discretely-distributed frailty, for example, when heterogeneity in lifetimes arises because of the presence of a random number of flaws in a unit or because of exposure to damage on a random number of occasions. In this work, we developed different frailty models applying some distributions belonging to Zero-Modified Power Series (ZMPS) family. In this context, with the use of the ZMPS distribution for frailty, we can notice the possibility of individuals with zero frailty, which corresponds to a limited failure model that contains a proportion of units that never fail (long-term survivors) or cure fraction model. The proposed model is applied to a set of real melanoma data.