Evaluating the Forecast Accuracy of Exchange Rate Volatility in Bangladesh Using ARCH Family of Models

Exchange rate is the price of one currency in terms of another currency. Modelling exchange rate volatility can play an important role in macroeconomic management for stability and growth. This paper examine the forecasting accuracy of ARCH family models for the monthly BDT/ USD exchange rate data from Bangladesh Bank over the period from August, 2004 to April, 2019. To find an appropriate model, several model selection criterion: Akaike information criteria (AIC) and Schwarz information criteria (SIC) and for measuring accuracy Root mean squared error (RMSE), Mean absolute error (MAE), Mean absolute percentage error (MAPE) and Theil inequality (TI) are used. Evaluation of models through these criteria suggest that GARCH (1,1) model is the best model for forecasting the monthly exchange rate volatility of Bangladesh and successfully overcome the leverage effect in the exchange rate