Title: Identifying shocks via time-varying volatility
Authors: Daniel Lewis - Federal Reserve Bank of New York (United States) [presenting]
Abstract: Under specific parametric assumptions, an $n$-variable structural vector auto-regression (SVAR) can be identified (up to $n!$ shock orderings) via heteroskedasticity of the structural shocks. We show that misspecification of the heteroskedasticity process can bias results derived from these identification schemes. We propose a new identification method that identifies the SVAR up to $n!$ shock orderings by using only moment equations implied by an arbitrary stochastic process for the variance. Unlike previous work, this result requires only weak technical conditions. In particular, it requires neither parametric assumptions nor the specification of variance regimes. We propose intuitive criteria to select among the orderings and show that this selection does not impact inference asymptotically. As an empirical illustration, we consider oil prices and their macroeconomic effects. This exercise strengthens his results by failing to reject his lower-triangular assumption and replicating his macroeconomic conclusions.