Title: Dealing with the statistical representation of DSGE models
Authors: Alessia Paccagnini - University College Dublin (Ireland) [presenting]
Abstract: Dynamic Stochastic General Equilibrium (DSGE) models are the main tool used in Academia and in Central Banks to evaluate the business cycle for policy and forecasting analyses. Despite the recent advances in improving the fit of DSGE models to the data, the misspecification issue remains. We deal with a specific aspect of the misspecification: the statistical representation of DSGE models. In particular, we discuss the case of DSGE models with a Vector Autoregressive Moving Average (VARMA) representation as a Data Generation Process. Considering several DSGE models to generate artificial pseudo-data, we compare results identifying shocks with VAR and Local Projection. We focus on the estimation and truncation errors induced by relying on a misspecified statistical representation.