Forecasting autoregressive time series under changing persistenceCreation-Date: 20100701

Changing persistence in time series models means that a structural change from nonstationarity to stationarity or vice versa occurs over time. Such a change has important implications for forecasting, as negligence may lead to inaccurate model predictions. This paper derives generally applicable recommendations, no matter whether a change in persistence occurs or not. Seven different forecasting strategies based on a biasedcorrected estimator are compared by means of a large-scale Monte Carlo study. The results for decreasing and increasing persistence are highly asymmetric and new to the literature. Its good predictive ability and its balanced performance among different settings strongly advocate the use of forecasting strategies based on the Bai-Perron procedure.