Measuring Interconnectedness between Financial Institutions with Bayesian Time-Varying Vector Autoregressions

Abstract

We propose a market-based framework that exploits time-varying parameter vector autoregressions to estimate the dynamic network of financial spillover effects. We apply it to financials in the Standard & Poor's 500 index and estimate interconnectedness at the sector and institution level. At the sector level, we uncover two main events in terms of interconnectedness: the Long Term Capital Management crisis and the 2008 financial crisis. After these crisis events, we find a gradual decrease in interconnectedness, not observable using the classical rolling window approach. At the institution level, our framework delivers more stable interconnectedness rankings over time than other market-based measures of systemic risk. Keywords

Bayesian forecasting of multivariate time series: scalability, structure uncertainty and decisions

“…The Primiceri's model, specialized for an analysis with macroeconomic variables, fits a variety of contexts well, in particular, fiscal and monetary policy discussions (see also Nakajima, 2011). In financial econometrics, Diebold and Yilmaz (2009) exploit the VAR model to assess spillover effects among financial variables such as stock price and exchange rates, and Geraci and Gnabo (2018) extend the framework with the TV-VAR.…”

Asymmetric Network Connectedness of Fears

“…Exploring these networks of good and bad fears, we show that the information contained in the novel forward-looking measures of network connectedness is valuable for forecasting macroeconomic conditions as well as economic uncertainty measures. In contrast to the previous literature measuring ex post systemic risk (see Billio et al, 2012;Diebold and Yılmaz, 2014;Hautsch et al, 2014;Härdle et al, 2016;Geraci and Gnabo, 2018), we aim to provide an ex ante systemic risk alarm bell that is useful for anticipating the propagation of risk in the financial sector. 1 Note that option prices are often used to measure the forward-looking volatility of the whole market in the financial literature (see Fleming et al, 1995;Christensen and Prabhala, 1998;Whaley, 2009).…”

COVID-19 Spreading in Financial Networks: A Semiparametric Matrix Regression Model

“…The authors show that connectivity increases in during 1999-2003 and in 2008-2009. Using a time-varying parameter vector autoregressive model (TVP-VAR), Geraci and Gnabo (2018) estimate a dynamic Granger Network in the S&P 500 market and find a gradual decrease in network connectivity not detectable using a rolling window approach. Similarly, in the framework 1 of forecast variance error decomposition (Diebold and Yilmaz, 2009;Diebold and Yılmaz, 2014).…”