by Marcin Kolasa and Michal Rubaszek
Narodowy Bank Polski and Warsaw School of Economics
A common practice in policymaking institutions using DSGE models for forecasting is to reestimate them only occasionally rather than every forecasting round. In this paper we ask how such a practice affects the accuracy of DSGE modelbased forecasts. To this end we use a canonical medium-sized New Keynesian model and compare how its quarterly real-time forecasts for the U.S. economy vary with the interval between consecutive reestimations. We find that updating the model parameters only once a year usually does not lead to any significant deterioration in the accuracy of point forecasts. On the other hand, there are some gains from increasing the frequency of reestimation if one is interested in the quality of density forecasts.
JEL Codes: C53, E37.
Full article (PDF, 27 pages, 298 kb)