15 March 2016
Anna Pestova and Mikhail Mamonov (Center for Macroeconomic Analysis and Short-term Forecasting, Moscow)
Conditional forecasting with BVAR model for Russia: the role of oil prices, sanctions, and monetary policy
In this paper we develop and provide an empirical test of Bayesian VAR model for Russian economy. Given the scarcity of literature on theoretically based forecasting models for Russia (DSGE), VAR models provide viable and flexible alternative. While most of the literature is focused on unconditional forecasting with BVAR, showing that their forecasting accuracy is comparable to other nonstructural models, a limited attention has been paid to conditional forecasts. We perform two counterfactual experiments with BVAR model for Russia: we estimate path of key macroeconomic variables conditioning on realized external conditions of 2012-2013 ("calm period") and 2014-2015 ("crisis period"). We show that the quality of conditional forecasts is higher than unconditional ones. In the "calm period" BVAR model shows a good approximation of the actual trajectories, while during the crisis forecasting becomes complicated due to monetary policy regime shifts. We found that the fall in oil prices does not fully explain the depth of the current recession in the Russian economy, which is partly driven by the limited access of Russian companies to international financial markets as a result of sanctions.
The seminars are open to all economists interested in the subject areas covered.
Please register in advance at email@example.com or by phone +358 10 831 2268.
Seminars will be held on Tuesdays at 10.30-11.30 unless otherwise indicated.
Visitors will be escorted from Rauhankatu 19 B (kirjasto bibliotek) entrance to the seminar room.