Evaluating Point and Density Forecasts of DSGE Models

Abstract

This paper investigates the accuracy of point and density forecasts of four DSGE models for inflation, output growth and the federal funds rate. Model parameters are estimated and forecasts are derived successively from historical U.S. data vintages synchronized with the Fed's Greenbook projections. Point forecasts of some models are of similar accuracy as the forecasts of nonstructural large dataset methods. Despite their common underlying New Keynesian modeling philosophy, forecasts of different DSGE models turn out to be quite distinct. Weighted forecasts are more precise than forecasts from individual models. The accuracy of a simple average of DSGE model forecasts is comparable to Greenbook projections for medium term horizons. Comparing density forecasts of DSGE models with the actual distribution of observations shows that the models overestimate uncertainty around point forecasts.

A Predictive Likelihood Approach to Bayesian Averaging

“…They use the predictive likelihood weighting scheme as well as equal weights to three variable forecasts (gross domestic product, infl ation and interest rate). Wolters (2012) extends Gerard and Nimark work by combining forecasts form four various DSGE models. The use of the predictive likelihood from the above mentioned models is complicated by the fact that the predictive likelihood does not have a closed form solution; see Eklund and Karlsson (2005).…”

Dealing with financial instability under a DSGE modeling approach with banking intermediation: A predictability analysis versus TVP-VARs

“…Interestingly, the TVP-VAR outranks the other models, whilst the DSGE model generates the highest RMSFE among the other speci…cations. As proposed by the recent literature of forecasting with DSGE models (Wolters, 2015;Kolasa and Rubaszek;, an avenue for future research in our comparison exercise is to assess the actual uncertainty of the estimated parameters by means of the density forecast.…”

Testing for Differences in Path Forecast Accuracy: Forecast-Error Dynamics Matter

“…12 The DSGE model forecasts are described in detail by Wolters (2015). While Wolters (2015) utilizes every forecast release per quarter to compute and evaluate point (and density)…”