A Bayesian analysis and estimation of random censored data: application to pharmacovigilance data on Malaria drugs

Abstract

In this study, we propose and derive a new Hierarchical Bayesian Weibull Regression model on random censored data using the Jeffrey’s prior. We derive the posterior density, marginal and obtain their kernels. The model parameters were estimated using Integrated Nested Laplace Approximation (INLA) and assess the model performance using Kulback Leibler Divergence and Deviance Information Criterion. The data is obtained from a pharmacovigilance study conducted by NAFDAC in collaboration with World Health Organization in Federal republic of Nigeria across six geopolitical zones. The shape parameter θ , were selected in the closed interval between zero and one with their respective priors distributions