Regime changes between Bitcoin and six other assets using Copula model with Markov switching

Examining the structure of dependence between financial assets and the effects of their Co-movement is one of the important issues in financial markets. The corresponding copula is one of the most computationally convenient ways to describe the dependency structure. This paper examines regime change probability and the best copula model between Bitcoin and six other assets from ۲۰۱۸ to ۲۰۲۱. First, using the ARMA-GARCH model, the marginal distribution functions for all assets and residuals are calculated. Then, by using the obtained residuals, ۱۱ models of copula and six models of combined Copula with Markov switching were implemented. The model that has the best function for constructing combined distribution functions is selected. Finally, the regime probabilities each time are calculated from the best-fitted model. The results show that in the study period, for Bitcoin-Ethereum, Bitcoin-Cardano, and Bitcoin-Gold pairs MS-CT, for Bitcoin-Binance coin and Bitcoin-Ripple pairs MS-CRG and MS-CN for Bitcoin-Oil pair have the best performance. Furthermore, the probabilities of regime change between each asset at each time were calculated and described.

Keywords:

Copula , Markov Switching , Bitcoin , Crypto , ARMA-GARCH