Applied Modeling Techniques and Data Analysis 2

5Forecasting Stochastic Volatility for Exchange Rates using EWMA

In risk management, foreign investors or multinational corporations are highly interested in knowing how volatile a currency is in order to hedge risk. In this chapter, using daily exchange rates and the exponential weighted moving average (EWMA) model, we perform volatility forecasting. We will investigate how the use of the available time series affects the forecasting, i.e. how reliable our forecasting is depending on the period of available data used. We will also test the effects of the decay factor appearing in the model used on the forecasts. The results show that, for the data used, it is optimal to use a larger value of the decay factor and also, for longer out-of-sample periods, the forecasts get closer to reality.

5.1. Introduction

When you move into a country that uses a different currency than yours, you need to change your currency by buying that of the country you are moving to. The rate at which you buy is called the exchange rate (Hull 2006), which is greater or less than one, depending on whether your currency is lower or greater in value than the currency you are buying.

Considering, for example, the currency of Sweden (the Swedish Krona: SEK) and the currency of Rwanda (the Rwandan Franc: RWF), the exchange rate for the pair SEK/RWF is greater than 1 because 1 SEK is nowadays nearly equivalent to 100 RWF. When the exchange rate is equal to one, both the considered currencies are equal in power, ...