Gold and Bitcoin

Herein, we have studied the impulse response of gold, Bitcoin, oil and stock markets before and after the COVID-19 based on the TVP-VAR model to determine whether gold or Bitcoin can be considered as a safe haven for oil and stock markets during the COVID-19 pandemic. First, we explore their time-varying impulse responses in different lag periods. Our findings indicate that gold can be used as a safe haven asset for oil and stock markets during the COVID-19 pandemic, but Bitcoin cannot be regarded as a safe haven. Moreover, gold’s safe haven property for the stock market becomes stronger when the pandemic spreads critically. Gold’s safe haven effect is better for the stock market initially, and the safe haven effects for oil strengthen later. Moreover, both gold and Bitcoin have a good hedging effect on oil before the COVID-19 pandemic, but only gold can hedge stock market shocks prior to the COVID-19 pandemic.
Furthermore, we use the ARMA model to eliminate the trend of new infected cases during the COVID-19 pandemic, and then obtain the residual sequence using the ARMA model. The ICSS method based on the residual sequence is used to select the structural breakpoints as the time points of the time-varying effects at different times. Through the timepoint impulse response analysis of four different structural breakpoints, it is found that the impulse response direction and intensity also vary under different events. Summarily, Bitcoin cannot be a safe haven against oil and stock market movements under the impact of the four special events. In contrast, gold can be considered as a safe haven for oil only under the impact of more than 90 million people infected worldwide, but gold can against the stock market shocks on the key points, except when the good news about the development of the vaccine was announced. Additionally, gold’s safe haven effects against stock market movement are stronger when the COVID-19 pandemic becomes more serious, namely, asymptomatic transmission. The aforementioned key time-point impulse effects support our discoveries in the time-varying impulse response.