Long-Run Linkages between US Stock Prices and Cryptocurrencies : A Fractional Cointegration Analysis

This paper applies fractional integration and cointegration methods to examine respectively the univariate properties of the four main cryptocurrencies in terms of market capitalization (BTC, ETH, USDT, BNB) and of four US stock market indices (S&P500, NASDAQ, Dow Jones and MSCI for emerging markets) as well as the possible existence of long-run linkages between them. Daily data from 9 November 2017 to 28 June 2002 are used for the analysis. The results provide evidence of market efficiency in the case of the cryptocurrencies but not of the stock market indices considered. They also indicate that in most cases there are no long-run equilibrium relationships linking the assets in question, which implies that cryptocurrencies can be a useful tool for investors to diversify and hedge when required in the case of the US markets