Bayesian Assessment of Identifying Restrictions for Heteroskedastic Structural VARs

We introduce a flexible Bayesian structural vector autoregressive model identified through heteroskedasticity, encompassing a range of volatility processes and allowing for additional identifying restrictions. Consequently, it enables comparisons across structural models with alternative sets of restrictions that just identify homoskedastic specifications. We develop a complete toolset for Bayesian inference, including a novel estimation algorithm, and an unbiased marginal data density estimator for locally identified models. Applying this apparatus to three U.S. monetary policy models, we document the empirical outperformance of models making use of two policy variables over those with a single one.

Co-author: Matthieu Droumaguet (Goldman Sachs, Hong Kong)  Website: bit.ly/tomaszwozniak

About Tomasz Woźniak

Tomasz Woźniak is an econometrician developing the methodology for empirical macroeconomic analyses. In his research, he investigates robust statistical methods for the assessment of economic hypotheses. He published a series of papers that look at Granger causality in the volatility of financial asset returns as well as in macroeconomic aggregates that exhibit nonlinear dynamics. Recently, he has worked on methods for using data to verify and compare alternative monetary policy theories represented as structural time series models. He works as a Lecturer at the Department of Economics of the University of Melbourne, is a co-founder of the Bayesian Analysis and Modeling Research Group and a co-organizer of an annual Melbourne Bayesian Econometrics Workshop.