Akademik Veri Yönetim Sistemi
Buletin Ekonomi Moneter dan Perbankan, cilt.27, sa.1, ss.113-132, 2024 (Scopus)
This study examines the validity of the efficient market hypothesis for the cryptocurrency market. We use the Exponential Generalized Autoregressive Conditional Heteroscedastic approach to examine the presence of different calendar anomalies i.e., the Halloween effect, the day-of-the-week (DOW) effect, and the month-of-the-year effect in the case of Bitcoin, Ethereum, XRP, Tether, and USD Coin. The findings show that there is no strong evidence of the Halloween effect. We find only robust Thursday and Saturday effects in the mean equation. In the case of the month-of-the-year effect, there is only a reverse January effect. More specifically, we note that April and February are statistically significant in the case of Bitcoin and Ethereum, respectively. Results obtained from the variance equations imply that September and October are the least risky months for investors.