A new approach to multi-step forecasting using dynamic stochastic general equilibrium models

TY - JOUR

T1 - A new approach to multi-step forecasting using dynamic stochastic general equilibrium models

AU - Kapetanios, George

AU - Price, Simon

AU - Theodoridis, Konstantinos

PY - 2015/11/1

Y1 - 2015/11/1

N2 - DSGE models are of interest because they offer structural interpretations, but are also increasingly used for forecasting. Estimation often proceeds by methods which involve building the likelihood by one-step ahead (h = 1) prediction errors. However in principle this can be done using different horizons where h> 1. Using the well-known model of Smets and Wouters (2007), for h = 1 classical ML parameter estimates are similar to those originally reported. As h extends some estimated parameters change, but not to an economically significant degree. Forecast performance is often improved, in several cases significantly.

AB - DSGE models are of interest because they offer structural interpretations, but are also increasingly used for forecasting. Estimation often proceeds by methods which involve building the likelihood by one-step ahead (h = 1) prediction errors. However in principle this can be done using different horizons where h> 1. Using the well-known model of Smets and Wouters (2007), for h = 1 classical ML parameter estimates are similar to those originally reported. As h extends some estimated parameters change, but not to an economically significant degree. Forecast performance is often improved, in several cases significantly.

KW - DSGE models

KW - Forecasting

KW - Multi-step errors

UR - http://www.scopus.com/inward/record.url?scp=84945969100&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2015.09.034

DO - 10.1016/j.econlet.2015.09.034

M3 - Article

AN - SCOPUS:84945969100

SN - 0165-1765

VL - 136

SP - 237

EP - 242

JO - ECONOMICS LETTERS

JF - ECONOMICS LETTERS

ER -