Title: The importance of supply and demand for oil prices: Evidence from identification by non-Gaussianity
Authors: Robin Braun - Bank of England (United Kingdom) [presenting]
Abstract: New evidence is provided on the relative importance of supply and demand shocks for fluctuations in oil prices. To estimate their effects, a structural vector autoregressive (SVAR) model for the global oil market is identified by non-Gaussianity. The identification approach is further refined by ruling out economically unreasonable oil price elasticities a priori. To incorporate this prior information in a coherent way, a new Bayesian SVAR is developed where the unknown distributions of the structural shocks are modeled nonparametrically. The empirical findings indicate that oil supply shocks have been minor drivers of oil prices post 1985. In terms of contributions to the long term forecast error variance of oil prices, the model arrives at median estimates between 1\% and 13\% depending on the exact prior specifications.