Testing for Granger Causality in Large Mixed-Frequency VARs

48 Pages Posted: 21 Jun 2016

See all articles by Thomas Götz

Thomas Götz

Deutsche Bundesbank

Alain Hecq

Maastricht University - Department of Economics

Stephan Smeekes

Maastricht University - Department of Quantitative Economics

Date Written: 2015

Abstract

We analyze Granger causality testing in a mixed-frequency VAR, where the difference in sampling frequencies of the variables is large. Given a realistic sample size, the number of high-frequency observations per low-frequency period leads to parameter proliferation problems in case we attempt to estimate the model unrestrictedly. We propose several tests based on reduced rank restrictions, and implement bootstrap versions to account for the uncertainty when estimating factors and to improve the finite sample properties of these tests. We also consider a Bayesian VAR that we carefully extend to the presence of mixed frequencies. We compare these methods to an aggregated model, the max-test approach introduced by Ghysels et al. (2015a) as well as to the unrestricted VAR using Monte Carlo simulations. The techniques are illustrated in an empirical application involving daily realized volatility and monthly business cycle fluctuations.

Keywords: Granger Causality, Mixed Frequency VAR, Bayesian VAR, Reduced Rank Model, Bootstrap Test

JEL Classification: C11, C12, C32

Suggested Citation

Götz, Thomas and Hecq, Alain and Smeekes, Stephan, Testing for Granger Causality in Large Mixed-Frequency VARs (2015). Bundesbank Discussion Paper No. 45/2015, Available at SSRN: https://ssrn.com/abstract=2797070 or http://dx.doi.org/10.2139/ssrn.2797070

Thomas Götz (Contact Author)

Deutsche Bundesbank ( email )

Wilhelm-Epstein-Str. 14
Frankfurt/Main, 60431
Germany

Alain Hecq

Maastricht University - Department of Economics

P.O. Box 616
Maastricht, 6200 MD
Netherlands

Stephan Smeekes

Maastricht University - Department of Quantitative Economics ( email )

P.O. Box 616
Maastricht, 6200 MD
Netherlands

HOME PAGE: http://www.personeel.unimaas.nl/s.smeekes

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

Paper statistics

Downloads
67
Abstract Views
554
Rank
608,356
PlumX Metrics