Comparative analysis of volatility structures of cryptocurrencies

With the emergence of Bitcoin and Blockchain technology, cryptocurrencies have begun to form. Cryptocurrencies are becoming increasingly popular because of the ability to trade quickly and securely with the Blockchain technology they use, eliminate brokerages and their low cost. As of May 3, 2021, there are 9527 cryptocurrencies and their market value has exceeded 2 trillion dollars. The prices of cryptocurrencies do not remain stable and fluctuations occur from time to time. The aim of this study is to contribute to the understanding of the volatility of cryptocurrencies. In this context, BTC, ETH, XRP, ADA, LTC, BCH, XLM, LINK, TRX and DOGE cryptocurrencies with high market value were selected by using ARCH, GARCH, ARCH-M, GARCH-M, IGARCH, EGARCH, TGARCH, APARCH and ACGARCH models mentioned in the theoretical section, their return series were created and their volatility was analyzed. In this study, the period of 01.01.2017-16.01.2021 for BTC, ETH, XRP, LTC; 01.01.2018-16.01.2021 for ADA, 04.08.2017-16.01.2021 for BCH, 03.02.2018-16.01.2021 for LINK, XLM data for the period 23.02.2017-16.01.2021, 15.11.2017-16.01.2021 for TRX and 04.06.2017-16.01.2021 for DOGE were used. As a result of the analyses, negative shocks occurring in BTC, ADA, LINK return series have more impact on volatility than positive shocks; It has been concluded that positive shocks in ETH, XRP, LTC, BCH, XLM, TRX, DOGE return series have more impact on volatility than negative shocks. Asymmetric conditional heteroscedasticity models were found to give more meaningful results than symmetric conditional heteroscedasticity models for the data used in this study.