Bitcoin Return and Volatility Memory Across Changing Market Efficiency

Summary

This study examines whether Bitcoin returns and volatility showed long memory from 2011 to 2017, and how that behavior changed over time. It estimates the Hurst exponent with rescaled range (R/S) and detrended fluctuation analysis (DFA), comparing their ability to capture changing persistence and informational efficiency.

The reported results indicate that R/S tends to identify long memory, while DFA more clearly distinguishes changes over time. Returns are persistent in the earlier part of the sample and appear more informationally efficient from 2014 onward. Volatility, measured using the log difference between intraday highs and lows, remains long-memory throughout the period. These findings suggest that returns and volatility may reflect different generating processes. The evidence is limited to the stated Bitcoin sample and methods; the summary gives no details on robustness checks or whether the detected persistence supports a profitable trading strategy.

Key ideas

• The study tracks Bitcoin return and volatility persistence from 2011 to 2017 using Hurst exponent methods.
• R/S analysis is prone to detecting long memory, while DFA better captures changes in efficiency over time.
• Bitcoin returns are persistent earlier in the sample and more informationally efficient from 2014 onward.
• The intraday high-low volatility measure exhibits long memory throughout the sample.
• Return and volatility patterns may arise from different underlying processes.

Tags

# The inefficiency of Bitcoin revisited: a dynamic approach


# The inefficiency of Bitcoin revisited: a dynamic approach









This letter revisits the informational efficiency of the Bitcoin market. In particular we analyze the time-varying behavior of long memory of returns on Bitcoin and volatility 2011 until 2017, using the Hurst exponent. Our results are twofold. First, R/S method is prone to detect long memory, whereas DFA method can discriminate more precisely variations in informational efficiency across time. Second, daily returns exhibit persistent behavior in the first half of the period under study, whereas its behavior is more informational efficient since 2014. Finally, price volatility, measured as the logarithmic difference between intraday high and low prices exhibits long memory during all the period. This reflects a different underlying dynamic process generating the prices and volatility.

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.