Modeling exchange rate volatility, using Univariate Generalized Autoregressive conditionally Hetroscedastic type models: evidence from Afghanistan

Abstract

In this study, an attempt is made to examine the performance of GARCH family models (including symmetric GARCH,GARCH-M, and asymmetric EGARCH models) in Forecasting the volatility behavior of Afghanistan foreign exchange rate. Daily foreign exchange rates of Afghani with USD data, ranging from 2018/09/01 to 2019/10/16 are used. Theoretically, the first order autoregressive behavior of the foreign exchange rate was evidenced in GARCH, GARCH-M and E-GARCH models while GARCH, GARCH-M and E-GARCH models support that previous day foreign exchange rate affected the current day exchange rate. Based on the comparison of the above models, found the GARCH (1,1) is the best model to explain the volatility of the return on the exchange of AFN with US Dollar