Economics Research Institute Study Paper
Utah State University Department of Economics
Copyright for this work is held by the author. Transmission or reproduction of materials protected by copyright beyond that allowed by fair use requires the written permission of the copyright owners. Works not in the public domain cannot be commercially exploited without permission of the copyright owner. Responsibility for any use rests exclusively with the user. For more information contact the Institutional Repository Librarian at firstname.lastname@example.org.
Exchange rates commonly exhibit periods of stability punctuated by infrequent, substantial adjustments. Statistically, this generates empirical distributions of exchange rate changes that have high peaks, long tails, and, sometimes, are asymmetric. Existing time-series estimation methods do not account for these characteristics satisfactorily. This paper introduces a more general GARCH model, based on the exponential generalized beta (EGB) family of distributions, which can accommodate most nonnormal characteristics of data, including leptokurtosis, skewness, and high peakedness, and yet remains tractable for estimation. Applied to daily U.S. dollar exchange rate data for six major currencies, the GARCH-EGB2 model uniformly outperforms conventional time-series models of exchange rate volatility.
Wang, Kai-Li; Fawson, Christopher; and Barrett, Christopher B., "A More General Approach to Modeling Exchange Rate Volatility" (1997). Economic Research Institute Study Papers. Paper 115.