Modeling Volatility of Exchange Rates Returns in the Nigerian Foreign Exchange Market in the Presence of Non-Gaussian Errors

Abstract

This study investigates volatility behaviour of exchange rates returns of Naira against CFA, Euro, Great British Pounds, US Dollar, West African Unit of Account (WAUA) and Japanese Yen in Nigeria using historical volatility approach as well as symmetric and asymmetric Autoregressive Conditional Heteroskedasticity (GARCH) models in the presence of non-Gaussian errors. The study utilizes daily quotations of these exchange rates from 12/11/2001 to 04/13/2018 making a total of 4008 observations each. Historical (annualized) volatility approach as well as symmetric GARCH (1,1) and asymmetric EGARCH (1,1) models were used to model the exchange rates return series. Results showed that CFA and USD have the highest and least annualized volatilities (market risk) respectively among the six exchange rates returns as measured by historical approach. The symmetric GARCH (1,1) model showed volatility clustering with evidence of shock persistence in the six exchange rates return series. The asymmetric EGARCH (1,1) model found evidence of asymmetry and leverage effects in the Nigerian foreign exchange market indicating that negative shocks (bad news) generate more volatility than positive shocks (good news) of similar magnitudes. All the estimated models were found to be stationary and mean reverting indicating the predictability and stability of the conditional variances of the foreign exchange rates returns. This result suggests that no matter how high or low the foreign exchange rates shall move in the exchange market, they shall eventually return to their long-run averages. Stationary and mean reverting stocks provide good and long term investment opportunities for investors.