ABSTRACT
We use a time-varying vector autoregressive model to investigate the dynamic effect of investor attention on Bitcoin speculation and then examine the association of this effect with five types of events in the Bitcoin market. The results indicate that investor attention has a positive effect on Bitcoin speculation and this effect changes with time and decays as lag phases increase. Policy-related events are the key factors that make this effect time-varying, while safety events have no obvious impact. Besides, our results find the existence of contrarian strategy in the Bitcoin market.
Acknowledgments
This research is supported by the National Natural Science Foundation of China (No. 72173018).
Disclosure statement
No potential conflict of interest was reported by the author(s).
Notes
1 The samples generated by MCMC are tested to be effective(see Appendix A).
2 The lag order selection process is shown in Appendix A.