Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
11023305 | Physica A: Statistical Mechanics and its Applications | 2019 | 16 Pages |
Abstract
This study empirically investigates the statistical characteristics and predictability of Bitcoin return and volatility. The distribution of Bitcoin returns and volatility display a fat right tail and high central parts. Bitcoin does not show the dynamic property of volatility persistence, contrary to stylized facts in financial time series. Also, the autoregressive model using past volatility does not well work in predicting changes in Bitcoin volatility for future periods. Investor sentiment regarding Bitcoin has a significant information value for explaining changes in Bitcoin volatility for future periods. These results suggest that Bitcoin appears to be an investment asset with high volatility and dependence on investor sentiment rather than a monetary asset.
Related Topics
Physical Sciences and Engineering
Mathematics
Mathematical Physics
Authors
Cheoljun Eom, Taisei Kaizoji, Sang Hoon Kang, Lukas Pichl,