Long-Range Return–Volatility Correlations in Bitcoin

Summary

The paper studies asymmetry between Bitcoin returns and volatility, measured using squared returns, across daily and higher-frequency data. It reports that return–volatility cross-correlations are mostly insignificant at the daily level. At higher frequencies, it finds a power-law pattern in the negative correlation between returns and subsequent volatility, which the authors interpret as evidence of long-range dependence.

The analysis also considers correlations between returns and absolute returns raised to different powers. The reported strength of these relationships varies with the chosen power, so the result depends on how volatility-like behavior is measured. The excerpt does not provide the data period, sampling details, statistical thresholds, or evidence of a trading application. These findings describe correlations and their frequency dependence; they do not establish causality or show that the relationships can be used profitably.

Key ideas

• Daily Bitcoin return–volatility cross-correlations are reported to be mostly insignificant.
• At higher frequencies, negative correlations between returns and future volatility are reported to follow a power law.
• The authors interpret the high-frequency pattern as long-range dependence.
• Correlation strength changes when volatility is represented by different powers of absolute returns.
• The excerpt reports statistical relationships without demonstrating causality or trading profitability.

Tags

# Power-Law Return-Volatility Cross Correlations of Bitcoin


# Power-Law Return-Volatility Cross Correlations of Bitcoin









This paper investigates the return-volatility asymmetry of Bitcoin. We find that the cross correlations between return and volatility (squared return) are mostly insignificant on a daily level. In the high-frequency region, we find thata power-law appears in negative cross correlation between returns and future volatilities, which suggests that the cross correlation is \revision{long ranged}. We also calculate a cross correlation between returns and the power of absolute returns, and we find that the strength of \revision{the cross correlations} depends on the value of the power.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.