Forecasting exchange rate volatility with monetary fundamentals: A GARCH-MIDAS approach

Abstract

The study examines the power of monetary fundamentals (interest rate and money supply growth) in forecasting daily exchange rate volatility in South Africa and Nigeria. The motivation is underscored by the relatively high level of exchange rate volatility of these two emerging economies and the need to effectively forecast it. Based on the available data frequency for the series, the GARCH-MIDAS model which allows for mixed data sampling thereby circumventing information loss or any associated bias is employed for both in-sample and out-of-sample forecast evaluations. The study finds that interest rates significantly predict exchange rate volatility in both countries, while money supply growth influences exchange rate movements only in South Africa. The result also indicates the long-run persistence of exchange rate volatility in both countries. Thus, the study concludes that monetary fundamentals play a crucial role in determining exchange rate volatility in both South Africa and Nigeria, providing useful insights for policy decision-making and risk mitigation strategies in these markets.