Bayesian estimate of parameters for ARMA model forecasting

Abstract

This paper presents a Bayesian approach to find the Bayes estimator of parameters for ARMA model forecasting under the normal-gamma prior assumption with a quadratic loss function in a mathematical expression. Conditional posterior predictive densityis obtainedbased on the normal-gamma priorandthe conditional predictive density whereas its marginal conditional posterior predictive density is obtained based on the conditional posterior predictive density. Furthermore, the Bayes estimator of parametersare derived from the marginal conditional posterior predictive density.