Can uncertainty indices predict Bitcoin prices? A revisited analysis using partial and multivariate wavelet approaches

Abstract

This paper uses bivariate and multivariate wavelet approaches to revisit the co-movements between the Volatility Uncertainty Index (VIX) and Bitcoin (BTC). This is achieved by accounting for the impacts of the three major global factors, namely the U.S. Economic Policy Uncertainty Index (EPU), the Crude Oil Volatility Index (OVX), and the Geopolitical Risk Index (GPR). To do this, we use Wavelet Coherence (WC), Cross Wavelet Transform (CWT), Power Wavelet Coherence (PWC), and Multiple Wavelet Coherence (MWC) approaches. The results show that the BTC-VIX relationship varies across time and at high and low frequencies. Moreover, we find positive (or in-phase) co-movements between both variables while a negative co-movement (out-of-phase) is observed at both high and low frequencies. VIX news has a prediction power on BTC price returns over different frequencies. The results of PWC and MWC show that OVX, EPU, and GPR factors affect the BTC-VIX nexus under different frequencies. Finally, correlations between BTC-uncertainty indices are dependent upon investment horizons. The results of our research are of interest and importance to investors, portfolio managers, and policy-makers, as the results have practical applications to inform their decision-making. - 2019 Elsevier Inc.