Multiperiod Bayesian forecasts forAR models

The multiperiod Bayesian forecast under the normal-gamma prior assumption for univariateAR models with strongly exogenous variables is investigated. A two-stage approximate method is proposed to provide an estimator of the posterior predictive density for any future observation in a convenient closed form. Some properties of the proposed method are proven analytically for a one-step ahead forecast. The precision of the proposed method is examined by using some simulated data and two sets of real data up to lead-twelve-ahead forecasts by comparison with a path sampling method. It is found that most of the results for the two discussed methods are rather close for short period forecast. Especially when sample size is sufficiently large, the estimated predictive density provided by the two-stage method asymptotically converges to the true density. A heuristic proof of this asymptotic property is also presented.