Exchange Rate Returns Standardized by Realized Volatility are (Nearly) Gaussian
Torben G. Andersen
Northwestern University - Kellogg School of Management; National Bureau of Economic Research (NBER); University of Aarhus - CREATES
Duke University - Finance; Duke University - Department of Economics; National Bureau of Economic Research (NBER)
Francis X. Diebold
University of Pennsylvania - Department of Economics; National Bureau of Economic Research (NBER)
Charles River Associates (CRA) - Utah Office
NBER Working Paper No. w7488
It is well known that high-frequency asset returns are fat-tailed relative to the Gaussian distribution tails are typically reduced but not eliminated when returns are standardized by volatilities estimated from popular models such as GARCH. We consider two major dollar exchange rates, and we show that returns standardized instead by the realized volatilities of Andersen, Bollerslev, Diebold and Labys (1999) are very nearly Gaussian. We perform both univariate and multivariate analyses, we trace the different effects of the different standardizations to differences in information sets, and we draw implications for the presence of jumps in exchange rate diffusions.
Number of Pages in PDF File: 23working papers series
Date posted: March 10, 2000
© 2013 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo7 in 0.563 seconds