Comparison of Symmetrical; Asymmetrical; and Logarithmic Models Using GARCH; GJR-GARCH; and EGARCH Method in Forecasting Indonesia–USA Currency Volatility
Comparison of Symmetrical; Asymmetrical; and Logarithmic Models Using GARCH; GJR-GARCH; and EGARCH Method in Forecasting Indonesia–USA Currency Volatility

Summary/Abstract: Aim: The main object of this study was to present a comparison between GARCH models, i.e. the standard GARCH model, asymmetric GJR-GARCH, and logarithmic EGARCH on exchange rate (IDR/USD) volatility. Methodology: The authors used GARCH, Glosten-Jagannathan-Runkle GARCH (GJR-GARCH) and Exponential GARCH (EGARCH) in estimating and forecasting exchange rate volatility. The variables were IDR/USD, Jakarta Stock Exchange Composite Index (JCI), World Oil Price, and Nominal Broad U.S. Dollar Index, while the data were daily, taken from World Bank, Federal Reserve Economic Data, and Indonesian Stock Exchange during 2006-2025. Results: The results revealed that in the GARCH method, there was high persistence of volatility, and the shocks were of long-lasting duration, but the model was symmetrical. The GJR-GARCH model showed that negative shocks have larger effects than positive shocks on IDR/USD but with problematic negative coefficients. Lastly, in the final comparison it was revealed that the EGARCH specifications were the most reliable in capturing asymmetric volatility dynamics, with strong evidence of leverage effects where negative shocks increase future volatility more than positive shocks. Implications and recommendations: As IDR/USD volatility took a long time to dissipate, and negative shocks had a significantly larger effect than positive shocks, this meant that the market reacted stronger on depreciation rather than on appreciation. Therefore, it was becoming essential for policymakers in Indonesia to provide an asymmetrical policy framework to prevent the negative shocks extending into a prolonged period of distrust by the market towards IDR. One of the actions to be taken was to increase interest rate. This was a preventive action to respond to depreciation, and at the same time acknowledging the asymmetric approach to responding to depreciation. Originality/value: The study compared three GARCH models to examine and forecast IDR/USD volatility, choosing one more statistically and economically reliable which makes this study unique. The findings present a comprehensive and methodologically established comparison that is unbiased and shows each model’s limitations and strengths. The study also provided additional contributions regarding integration of broad variables into the models, with the use of world oil price, JCI, and Nominal Broad US Index as variables.

• Details
• Contents