Quantile prediction for Bitcoin returns using financial assets’ realized measures

Tabito Kawakami

Finance Research Letters, 2023, vol. 55, issue PA

Abstract: This paper explores which properties of financial asset prices drive Bitcoin’s return distributions, using quantile regressions with lagged realized moment measures of various financial assets. The result shows that Bitcoin’s lagged realized volatility predicts its return distributions very well, revealing Bitcoin’s aspect as a risk asset. Moreover, its lagged realized kurtosis plays some role in prediction in recent periods. In contrast, other financial assets’ realized measures have limited predictive power, which implies the relative uniqueness of Bitcoin’s price movements. Finally, out-of-sample predictions using lasso quantile regressions confirm the robust predictive power of lagged Bitcoin variables even in the Covid-19 period.

Keywords: Quantile regression; Realized measures; Value-at-risk; Prediction; Lasso; Bitcoin (search for similar items in EconPapers)
JEL-codes: C14 C21 C53 G17 G32 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612323002167
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:55:y:2023:i:pa:s1544612323002167

DOI: 10.1016/j.frl.2023.103843

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().