Bayesian Estimation of Measurement Error Models with Longitudinal Data

In this paper, Bayesian inferences for semiparametric measurement error models (MEs) for longitudinal data are investigated. A semiparametric Bayesian approach combining the stick-breaking prior and the Gibbs sampler together with the Metropolis-Hastings algorithm is developed for simulating observations from the posterior distributions and producing the joint Bayesian estimates of unknow parameters and measurement error. We obtain Bayesian estimations of parameters and covariates subject to MEs. Two simulation studies are presented to illustrate our proposed methodologies.