Analysis of Dagum Model for Software Reliability Using Markov Chain Monte Carlo Method

摘要

Markov Chain Monte Carlo (MCMC) method has been used to estimate the parameters of Dagum model depended on a complete sample. In order to obtain Bayes estimates of parameters for the Dagum model using MCMC simulation method in OpenBUGS, independent non-informative and informative set of priors for Dagum parameters are assumed to obtain samples from the posterior density function. In addition, the estimates always exist and statistically consistent and their probability intervals are convenient to construct. Applying MCMC to estimate parameters of Dagum is elaborated. A real software reliability data set is considered to illustrate the methods of inference discussed in this paper.