Modeling the exchange rate volatility, using generalized autoregressive conditionally heteroscedastic (GARCH) type models: Evidence from Pakistan

Abstract

Increasing role of foreign exchange (FOREX) rate in corporate decision making is becoming famous in the developing economies, where FOREX rate volatility occupied a central position all over the world in investment decision. In a scenario, where FOREX rate volatility is equally helpful in many micro as well as macro economic decision-making (remembering historical roots of some of the financial crises were traced in the FOREX rate volatility). In this study, an attempt is made to examine the performance of GARCH family models (including symmetric GARCH-M, asymmetric EGARCH and TARCH models) in forecasting the volatility behavior of Pakistani FOREX market. Daily FOREX rates data, ranging from January, 2001 to December, 2009 was put to statistical manipulation to examine the FOREX volatility behavior in Pakistan. Theoretically, the first order autoregressive behavior of the FOREX rate was evidenced in GARCH-M and E-GARCH models while the GARCH-M model supports that previous day FOREX rate affected the current day exchange rate. The EGARCH-based evaluation of FOREX rates showed asymmetric behavior of volatility, where TARCH model showed insignificance but detailed exploratory analysis of the FOREX rate behavior requires prolonged study by applying advance models. Key words: Exchange rate, GARCH-M, TARCH, EGARCH, volatility, Pakistan.