No abstract

Purpose The purpose of this paper is to examine the day-of-the-week effects of Bitcoin (BTC) markets on the exchange level from January 2014 to September 2018. Design/methodology/approach The in-depth study on the day-of-the-week effects is conducted by using data consisting of Bitcoin prices denominated in 20 fiat currencies from 23 Bitcoin trading exchanges through the method of rolling sample for calendar effect proposed by Zhang et al. (2017). Findings It is shown by the empirical results that different patterns of the day-of-the-week effects are observed on Bitcoin denominated in various fiat currencies by referring to the price data collected from exchanges. Furthermore, the patterns of the day-of-the-week effects are also available after adjusting Bitcoin prices denominated in domestic currencies into USD. Research limitations/implications Because of the discontinuity of data for some daily return series, estimation with dynamic variance is not applicable. It is assumed that the error item follows normal distribution with constant variance. Originality/value The day-of-the-week effects are wide-spread in Bitcoin markets, and they are not mainly caused by movements of foreign exchange rates. Actually, empirical findings in this study provide evidence for inefficiency of Bitcoin markets.

In this study, an investigation is conducted into the phenomenon of price clustering in Bitcoin (BTC) denominated in the Japanese yen (JPY). It answers two questions using tick-by-tick data. The first is whether price clustering exists in BTC/JPY transactions, and the other is how the scale of price clustering varies throughout a trading day. With the assistance of statistical measures, the last two digits of BTC price were discovered to cluster at the numbers that end with ’00’. In addition, the scales of BTC/JPY clustering at ’00’ tended to decline at the specific hour intervals. This study contributes to the emerging literature on price clustering and investor behavior.

Purpose The purpose of this paper is to investigate how the selection of return distribution impacts estimated volatility in China’s stock market. Design/methodology/approach The authors use a Bayesian analysis of fat-tailed stochastic volatility (SV) model with Student’s t-distribution, and conduct an out-of-sample test with realized volatility. Findings Empirical analysis results indicate that fat-tailed SV model performs better in capturing the dynamics of daily returns. The authors find that asymmetry, holiday and day of the week effects are detected in estimated volatility. However, the out-of-sample comparison shows that fat-tailed SV models fail to outperform SV models with normal distribution in fitting and predicting realized volatility. Originality/value The contribution of this paper to existing literature is twofold. First, it proves that fat-tailed SV models with Student’s t-distribution perform better than normally distributed SV models in fitting daily returns of China’s stock market. Second, this paper takes asymmetry, holiday and day of the week effects into consideration at the same time in the fat-tailed SV model.

No abstract