Volatility has been one of the most active and successful areas of research in time series econometrics and economic forecasting in recent decades. Loosely speaking, volatility is defined as the average magnitude of fluctuations observed in some phenomenon over time. Within the area of economics, this definition narrows to the variability of an unpredictable random component of a time series variable. Typical examples in finance are returns on assets, such as individual stocks or a stock index like the S&P 500 index. As indicated by the quote from Campbell et al. (1997), (financial market) volatility is central to financial economics. Since it is the most common measure of the risk involved in investments in traded securities, it plays a crucial role in portfolio management, risk management, and pricing of derivative securities including options and futures contracts. Volatility is therefore closely tracked by private investors, institutional investors like pension funds, central bankers and policy makers. For example, the so-called Basel accords contain regulations where banks are required to hold a certain amount of capital to cover the risks involved in their consumer loans, mortgages and other assets. An estimate of the volatility of these assets is a crucial input for determining these capital requirements. In addition, the financial crisis in 2007-2008 has proven that the impact of financial market volatility is not only limited to the financial industry. It shows that volatility may be costly for the economy as a whole. For example, extreme stock market volatility may negatively influence aggregate investments behavior, in particular as companies often require equity as a source of external financing. This thesis contributes to the volatility literature by investigating several relevant aspects of volatility. First, we focus on the parameter estimation of multivariate volatility models, which is problematic if the number of considered assets increases. Second, we consider the question what exactly causes financial market volatility? In this context, we relate volatility with various types of information. In addition, we pay attention to modeling volatility, by adapting volatility models such that they allow for including possible exogenous variables. Finally, we turn to forecasting techniques of volatility, with the focus on the combination of density forecasts.

financial markets, market volatility, time series, fluctuations, forecasting, GARCH models
D.J.C. van Dijk (Dick)
Thela Thesis, Amsterdam , Erasmus University Rotterdam
Tinbergen Instituut Research Series
This book is no. 574 of the Tinbergen Institute Research Series, established through cooperation between Thela Thesis and the Tinbergen Institute.
Erasmus School of Economics

Opschoor, A. (2014, February 20). Understanding Financial Market Volatility (No. 574). Tinbergen Instituut Research Series. Erasmus University Rotterdam. Retrieved from http://hdl.handle.net/1765/50526