An extreme value analysis of the tail relationships between returns and volumes for high frequency cryptocurrencies

Abstract

This paper investigates both the extreme dependence and correlation between high frequency cryptocurrency (Bitcoin and Ethereum, versus the Euro and US Dollar) returns and transaction volumes, at the extreme tails associated with booms and busts in the cryptocurrency markets. We apply an extreme value theory (EVT) approach, and highlight how these results assist traders and practitioners who rely on such technical indicators in their trading strategies – especially in times of extreme market turbulence or irrational market exuberance. Our findings contradict the belief in Wall Street that volume can significantly influence price levels and from an economic perspective our model reveals weak positive correlation between return and volume at the tails, which suggests that a misinterpretation among market participants can cause cryptocurrency markets to be relatively illiquid, thus leading to extreme price movements. Relating our statistical findings to economic models, we find that our empirical results are consistent with the explanation of market crashes based on trade misinterpretation.