Dear Stéphane, I may be wrong, but it looks to me as if the Bayesian forecasts provided for DSGE-VARs are not based on the VAR, but on the DSGE model itself (using dsgesmoother.m). Is this correct and intended or is it a bug? Best, Johannes -------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de