Large Bayesian VARs: A Flexible Kronecker Error Covariance Structure

32 Pages Posted: 10 Nov 2015

See all articles by Joshua C. C. Chan

Joshua C. C. Chan

University of Technology Sydney (UTS) - UTS Business School; Purdue University

Date Written: November 1, 2015

Abstract

We introduce a class of large Bayesian vector autoregressions (BVARs) that allows for non-Gaussian, heteroscedastic and serially dependent innovations. To make estimation computationally tractable, we exploit a certain Kronecker structure of the likelihood implied by this class of models. We propose a unified approach for estimating these models using Markov chain Monte Carlo (MCMC) methods. In an application that involves 20 macroeconomic variables, we find that these BVARs with more flexible covariance structures outperform the standard variant with independent, homoscedastic Gaussian innovations in both in-sample model-fit and out-of-sample forecast performance.

Keywords: stochastic volatility, non-Gaussian, ARMA, forecasting

JEL Classification: C11, C51, C53

Suggested Citation

Chan, Joshua C. C. and Chan, Joshua C. C., Large Bayesian VARs: A Flexible Kronecker Error Covariance Structure (November 1, 2015). Available at SSRN: https://ssrn.com/abstract=2688342 or http://dx.doi.org/10.2139/ssrn.2688342

Joshua C. C. Chan (Contact Author)

Purdue University

West Lafayette, IN 47907-1310
United States

University of Technology Sydney (UTS) - UTS Business School ( email )

Sydney
Australia

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
54
Abstract Views
623
Rank
676,215
PlumX Metrics