BAYESIAN ANALYSIS OF UNEMPLOYMENT DURATION DATA IN THE PRESENCE OF RIGHT AND INTERVAL CENSORING

In this paper, Bayesian inference for unemployment duration data in the presence ofright and interval censoring, where the proportionality assumption does not hold, is discussed. Inorder to model these kinds of duration data with some explanatory variables, Bayesian loglogistic,log-normal and Weibull accelerated failure time (AFT) models are used. In thesemodels, sampling from the joint posterior distribution of the unknown quantities of interest areobtained through the use of Markov chain Monte Carlo (MCMC) methods using the availableWinBUGS software. These models are also applied for unemployment duration data of Iran in2009. The models are compared using deviance information criterion (DIC). Two new sensitivityanalyses are also performed to detect: (1) the modification of the parameter estimates withrespect to the alteration of generalized variance of the multivariate prior distribution of regressioncoefficients, and (2) the change of the posterior estimates with respect to the deletion ofindividuals with high censoring values using Kullback-Leibler divergence measure.