• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Working paper

Forecasting Russian macroeconomic indicators with BVAR

This paper evaluates the forecast performance of Bayesian vector autoregressions on Russian data. We estimate BVAR models  of different size and compare the accuracy of their out-of-sample forecasts with those obtained with unrestricted VARs and RW with drift. We show that many Russian macroeconomic indicators can be forecast by Bayesian VAR more accurately than by competitor models. However, contrary to several other studies, we do not confirm that relative forecast error monotonically decreases with the dimension of the sample. In half of those cases where BVAR appears to be the most accurate model, a small-dimensional BVAR outperforms its high-dimensional counterpart.