Glossary

Volatility Spillover

The transmission of volatility from one market or asset to another. Diebold and Yilmaz (2012) proposed a framework based on generalised VAR forecast-error variance decompositions to measure total and directional volatility spillovers.

Definition

Why It Matters

In an interconnected global financial system, volatility in one market does not stay confined; it transmits across borders and asset classes. Understanding volatility spillovers is essential for portfolio diversification, risk management, and macroprudential policy. The Diebold-Yilmaz framework provides a transparent, model-based decomposition that distinguishes between total spillovers, directional spillovers (from market i to market j and vice versa), and net spillovers, enabling researchers and policymakers to identify which markets are transmitters and which are receivers of volatility shocks.

Example

Applying the Diebold-Yilmaz spillover index to daily volatility of BIST-100, S&P 500, FTSE-100, and Nikkei-225 returns from 2015 to 2023 reveals that total spillover index spikes from 35% in calm periods to over 70% during the COVID-19 crisis. The S&P 500 is the largest net transmitter of volatility, while BIST-100 is a net receiver, particularly susceptible to spillovers from European markets.

Related Terms

Software Notes

SPSS: Not natively supported; use R integration for volatility spillover analysis.
R: Use the spillover() function from the connectedness package to implement the Diebold-Yilmaz framework. For GARCH-based volatility estimation prior to spillover analysis, use rugarch::ugarchfit().
Stata: No built-in command for the Diebold-Yilmaz index. Implement manually using VAR estimation followed by generalised forecast-error variance decomposition, or use R integration.