Identification of Structural Vector Autoregressions by Stochastic Volatility

Abstract

We propose to exploit stochastic volatility for statistical identification of structural vector autoregressive models (SV-SVAR). We discuss full and partial identification of the model and develop efficient Expectation Maximization algorithms for Maximum Likelihood inference. Simulation evidence suggests that, compared to alternative models, the SV-SVAR works well in identifying structural parameters also under misspecification of the variance process. We apply the model to study the importance of oil supply shocks for driving oil prices. Since shocks identified by heteroskedasticity may not be economically meaningful, we exploit the framework to test instrumental variable restrictions which are overidentifying in the heteroskedastic model. Our findings suggest that conventional supply shocks are negligible drivers of oil prices, while news shocks about future supply account for almost all the variation.