报告地点：行健楼学术活动室526
Abstract: Compared with the widely used mean-based models, the prediction based on median autoregression is often more robust for time series forecasting. Motivated by the asymmetric exponential power working likelihood approach in Bayesian quantile regression, we propose a Bayesian median autoregression using the asymmetric exponential power error. The proposed model can better deal with outliers than the existing Bayesian median autoregression with the Laplace error. An adaptive independent Metropolis-Hastings algorithm is used for the parameter estimation. A simple and effective approximate forecasting procedure is proposed based on the Watanabe-Akaike information criterion in the framework of Bayesian model averaging. Model assessment, order selection, and out-of-sample predictive accuracy are all discussed. Finally, three examples of macroeconomic data are analyzed to show the superior performance of the proposed model.
