BAYESIAN ESTIMATION IN SHARED COMPOUND POISSON FRAILTY MODELS

  • David D. Hanagal Department of Statistics, Savitribai Phule Pune University, Pune, India
  • Asmita T. Kamble Modern College of Arts, Science and Commerce, Pune, India
Keywords: Bayesian Estimation, Compound Poisson Frailty, Markov Chain Monte Carlo, Shared Frailty

Abstract

In this paper, we study the compound Poisson distribution as the shared frailty distribution and two different baseline distributions namely Pareto and linear failure rate distributions for modeling survival data. We are using the Markov Chain Monte Carlo (MCMC) technique to estimate parameters of the proposed models by introducing the Bayesian estimation procedure. In the present study, a simulation is done to compare the true values of parameters with the estimated values. We try to fit the proposed models to a real life bivariate survival data set of McGrilchrist and Aisbett (1991) related to kidney infection. Also, we present a comparison study for the same data by using model selection criterion, and suggest a better frailty model out of two proposed frailty models.

 

Downloads

Download data is not yet available.
Published
2015-06-25
Section
Articles