GARCH Model With Fat-Tailed Distributions and Bitcoin Exchange Rate Returns

9 Pages Posted: 16 Sep 2020

See all articles by Zi-Yi Guo

Zi-Yi Guo

Vanderbilt University - College of Arts and Science - Department of Economics

Date Written: July 2017

Abstract

In the era of diminishing power from US dollar and increasing competition among world currencies, Bitcoin, as a completely new concept as a medium of exchange, has received increasing attentions over the world. Nowadays, Bitcoin also becomes an investment vehicle, which carries attractive opportunities but also significant risks for the investment community. In this paper, we have compared the empirical performance of a newly-developed heavy-tailed distribution, the normal reciprocal inverse Gaussian (NRIG), with the most popular heavy-tailed distribution, the Student’s t distribution, under the GARCH framework in fitting the daily Bitcoin exchange rate returns. Our results indicate the heavy-tailed distribution has better performance in capture the daily Bitcoin exchange rate returns dynamics than the standard normal distribution. Our results also show the older fashioned Student’s t distribution still performs better than the new heavy-tailed distribution.

Keywords: Student’s T Distribution; GARCH Model; Bitcoin

JEL Classification: C22; C52; G17

Suggested Citation

Guo, Zi-Yi, GARCH Model With Fat-Tailed Distributions and Bitcoin Exchange Rate Returns (July 2017). Available at SSRN: https://ssrn.com/abstract=3666106 or http://dx.doi.org/10.2139/ssrn.3666106

Zi-Yi Guo (Contact Author)

Vanderbilt University - College of Arts and Science - Department of Economics ( email )

Box 1819 Station B
Nashville, TN 37235
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
42
Abstract Views
241
PlumX Metrics