Corresponding Quantlets to master's thesis 'BTC and ETH return dependencies over time with time-varying copulae'
Abstract:
The purpose of this paper is to describe the interrelation of the returns between the two largest cryptocurrencies by market capitalization: Bitcoin (BTC) and Ethereum (ETH). The dependence between them is analyzed via GARCH-copula models, which are very popular and flexible tools in financial econometrics. For this study, not only static but also time-varying copulae are applied as dependence may not be constant over time. Time-varying copula models are more flexible and allow one to capture the temporal dependence between assets. Overall, the results show that the time-varying rotated Gumbel (180 degrees) and the time-varying symmetrized Joe Clayton (SJC) copulas are the best models, indicating that BTC and ETH extreme returns are associated. It was also observed that tail dependence is stronger when BTC and ETH returns are low than when they are high.