期刊名称：Brazilian Journal of Probability and Statistics
印刷版ISSN：0103-0752
出版年度：2004
卷号：18
期号：1
页码：19-35
出版社：Brazilian Statistical Association
摘要：Recurrent event data arises in several areas, such as, biomet-rics, criminology, demography, industrial reliability and production. In thiskind of data it is reasonable to presume that there is dependency among theobservations related to the same sub ject. Such dependency can be modelledby allowing a random e.ect, usually called frailty term, in the mo delling.In this paper the recurrent event problem is treated under the homogeneousPoisson process approach, but with a frailty term. A Bayesian inferenceprocedure based on Markov Chain Monte Carlo Methods is developed. Themethodology is illustrated on a real data set
