How risky are cryptocurrencies?

ABSTRACT

Volatility in the cryptocurrency market is an extremely important indicator for investors, as it allows them to manage their investment risk and define strategies that will result in profit maximization. Thus, this study focuses on determine which of the GARCH, EGARCH, and TGARCH models is the optimal model that best describes the daily returns’ volatility of MATIC, SOL, BTT, and VET – four cryptocurrencies with relatively limited presence in the market compared to Bitcoin. The optimal model is selected by using the AIC statistical quality criterion. For the chosen sample period, empirical evidence suggests that EGARCH(1,1) and GARCH(1,1) are the most suitable models for describing the returns’ volatility of MATIC and VET, respectively. In the cases of SOL and BTT, the lack of success in validating all the assumptions needed to apply GARCH models reveals that these models are not the most adequate for describing the cryptocurrencies under study.

KEYWORDS:

• Cryptocurrencies
• volatility
• GARCH models
• conditional heteroskedasticity
• stylized facts of volatility

JEL CLASSIFICATIONS:

• G10
• G20

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This paper/research is financed by Portuguese national funds through FCT-Fundação para a Ciência e a Tecnologia, I.P., project number UID/ECO/00685/2016.