A0964
Title: What events matter for exchange rate volatility
Authors: Igor Martins - Orebro University (Sweden) [presenting]
Abstract: The purpose is to expand stochastic volatility models by proposing a data-driven method to select the macroeconomic events most likely to impact volatility. The effect of macroeconomic events on exchange rate volatility in multiple countries is identified and quantified in multiple countries using high-frequency currency returns while accounting for persistent stochastic volatility effects and seasonal components that capture time-of-day patterns. Due to the hundreds of macroeconomic announcements and their lags, sparsity-based methods are relied on to select relevant events for the model. The contribution to the exchange rate literature is in four ways. First, the macroeconomic events that drive currency volatility are identified, their effect is estimated and connected to macroeconomic fundamentals, and how they can be linked to lower-frequency currency returns is shown using a model averaging argument. Second, a connection between intraday seasonality, trading volume, and opening hours of major markets across the globe is found, and a simple labor-based argument is provided for the pattern found. Third, it is shown that the inclusion of macroeconomic events and seasonal components is key for forecasting exchange rate volatility. Fourth, applying the proposed model for multiple currencies alongside a dynamic copula yields a Sharpe ratio 3.5 times higher than using standard SV and GARCH models.
