Measuring Dynamic Connectedness with Large Bayesian VAR Models

30 Pages Posted: 16 Jan 2018

See all articles by Dimitris Korobilis

Dimitris Korobilis

University of Glasgow - Adam Smith Business School

Kamil Yilmaz

Koc University

Date Written: January 10, 2018

Abstract

We estimate a large Bayesian time-varying parameter vector autoregressive (TVP-VAR) model of daily stock return volatilities for 35 U.S. and European financial institutions. Based on that model we extract a connectedness index in the spirit of Diebold and Yilmaz (2014) (DYCI). We show that the connectedness index from the TVP-VAR model captures abrupt turning points better than the one obtained from rolling-windows VAR estimates. As the TVP-VAR based DYCI shows more pronounced jumps during important crisis moments, it captures the intensification of tensions in financial markets more accurately and timely than the rolling-windows based DYCI. Finally, we show that the TVP- VAR-based index performs better in forecasting systemic events in the American and European financial sectors as well.

Keywords: Connectedness, Vector Autoregression, Time-Varying Parameter Model, Rolling Window Estimation, Systemic Risk, Financial Institutions

JEL Classification: C32, G17, G21

Suggested Citation

Korobilis, Dimitris and Yilmaz, Kamil, Measuring Dynamic Connectedness with Large Bayesian VAR Models (January 10, 2018). Available at SSRN: https://ssrn.com/abstract=3099725 or http://dx.doi.org/10.2139/ssrn.3099725

Dimitris Korobilis

University of Glasgow - Adam Smith Business School ( email )

40 University Avenue
Gilbert Scott Building
Glasgow, Scotland G12 8QQ
United Kingdom

HOME PAGE: http://https://sites.google.com/site/dimitriskorobilis/

Kamil Yilmaz (Contact Author)

Koc University ( email )

Rumeli Feneri Yolu
Sariyer
Istanbul, 34450
Turkey
+90 212 338 1458 (Phone)
+90 212 338 1653 (Fax)

HOME PAGE: http://https://sites.google.com/view/kamilyilmaz/

Register to save articles to
your library

Register

Paper statistics

Downloads
133
Abstract Views
637
rank
220,213
PlumX Metrics