Bitcoin volatility was investigated with various symmetric and asymmetric models in the study. In addition, value at risk (VaR) was calculated by using the Kupiec LR test and the error prediction performances of the models were compared. As a result of the work, the long memory of volatility in Bitcoin returns was found. It means the cryptocurrency market is not efficient. According to the FIAPARCH asymmetric model, it was determined that positive information shocks reaching the Bitcoin market increased volatility more than negative information shocks. Comparing the error prediction performance of the models by calculating VaR, the HYGARCH model prediction results were found to be superior to other models included in the study. Thus, it was determined that the most suitable model in predicting the volatility, namely the risk of Bitcoin in short and long positions for those who consider investing in Bitcoin, is the asymmetric model HYGARCH.
Primary Language | English |
---|---|
Subjects | Business Administration |
Journal Section | MAIN SECTION |
Authors | |
Publication Date | June 30, 2020 |
Submission Date | April 25, 2020 |
Published in Issue | Year 2020 Volume: 22 Issue: 2 |
Authorship
MBDD follows the guidelines in COPE Authorship Guideline to ensure fair recognition of contributions to a research paper (https://publicationethics.org/guidance/discussion-document/authorship ). Authorship carries both credit and responsibility, and it is essential that all listed authors have made significant contributions to the research.
For multi-author studies, the Contributions of Authors must be declared after the conclusion and before the bibliography of the paper. The authors' initials and last names should be used to indicate which author contributed to which part of the manuscript. Details can be found by clicking the “Article Submission Checklist” button. The authors can acknowledge contributions that do not merit authorship.
The author(s) should disclose the use of generative Artificial Intelligence (AI) and AI-assisted tools in design and implementation of the research. Such use need to be disclosed within the methodology section of the manuscript. Use of AI does not preclude the manuscript from publication, rather provides a transparent picture of the research.