Modelling Exchange Rate Volatility Using GARCH Model: An Empirical Analysis for Vietnam

Abstract

This paper empirically investigates the nature of exchange rate volatility in the context of Vietnam FX market. The study uses monthly data on exchange rates of Vietnamese Dong in term of major currencies such as US Dollar, British Pound, Japanese Yen and Canadian Dollar. The empirical analysis has been carried out for the period from Jan 1990 to Jun 2017, for a total of 330 observations. The exchange rate volatility of Vietnamese Dong against foreign currencies are estimated using GARCH models. Results show that ARMA(1,0)-GARCH(1,2) models with Student-t error distribution are well adequate models to capture the mean and volatility process of USD-VND and GBP-VND exchange rate returns, while ARMA(1,0)-GARCH(1,1) models with Student-t distribution are reasonably adequate models to capture the mean and volatility process of JPY-VND and CAD-VND exchange rate returns. The results also show that the exchange rate returns are rejected to follow Gaussian distribution at 1% significant level, and all four exchange rate return series maintain high persistence and volatility clustering.