The inefficiency of Bitcoin revisited: a dynamic approach

TL;DR

This paper analyzes the time-varying informational efficiency of Bitcoin from 2011 to 2017 using the Hurst exponent, revealing differences in return and volatility behaviors and comparing methods for detecting long memory.

Contribution

It compares R/S and DFA methods for analyzing long memory in Bitcoin returns and volatility, highlighting DFA's superior discrimination of efficiency variations over time.

Findings

R/S method is prone to detect long memory.

DFA method better discriminates efficiency variations.

Returns are persistent early on, more efficient after 2014.

Abstract

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.