The day-of-the-week effect on Bitcoin return and volatility

doi:10.1016/j.ribaf.2019.02.003

Research in International Business and Finance

Volume 49, October 2019, Pages 127-136

https://doi.org/10.1016/j.ribaf.2019.02.003 Get rights and content

Abstract

This study investigates the day-of-the-week effect on both return and volatility of Bitcoin (BTC) from January 2013 to December 2018 using daily data obtained from CoinDesk Bitcoin Price Index. Estimation results suggest that the day-of-the-week effect in return equation varies with sample periods, while significantly high volatilities are observed on Monday and Thursday. Hence, the significantly high mean return of Bitcoin on Monday is found as a response to higher volatility. Besides, the day-of-the-week effect on both return and volatility remains robust after accounting for stock market returns (S&P 500; SSEC; Nikkei 225) and foreign exchange market returns (USD/CNY; USD/JPY; EURO/USD). Finally, no asymmetry effect on volatility is discovered here.

Graphical abstract

Introduction

Bitcoin has been a prominent cryptocurrency since its introduction (Nakamoto, 2008) because it is decentralized without the need for intermediaries. At present, Bitcoin is not only a digital currency, but also a new financial asset traded online daily, with markets open for 24 h. Bitcoin exhibits some properties to those of traditional financial assets (Dyhrberg, 2016a, Bouri et al., 2017b). However, Bitcoin is not backed by any central bank or government, and it shows much higher volatility than major currencies (Baur and Dimpfl, 2017). The rapid global spread of Bitcoin trading not only arouses the attention from investors and the media, but it is also a topic of concern in recent financial researches.

The day-of-the-week effect means that returns are different on certain weekdays, which is also known as one of the calendar anomalies in financial markets, especially in stock and foreign exchange markets. The existence of the day-of-the-week effect is not consistent with the Efficient Market Hypothesis (EMH) that investors could not obtain abnormal returns based on publicly released information. There are many potential explanations proposed for this calendar anomaly, e.g. measurement error, spillover from other markets, information releases after close, investors’ psychology, etc. As Bitcoin exchanges operate 24/7 without weekends and holidays, return distributions of Bitcoin on weekdays should be the same in calendar time.

The main aim of this study is to investigate the existence of the day-of-the-week effect on both return and volatility of Bitcoin. The day-of-the-week effect has already been observed in traditional financial markets, whereas the day-of-the-week effect on volatility of Bitcoin has been rarely investigated. Thus, this study tries to explain the day-of-the-week effect on both return and volatility with risks from stock and foreign exchange markets. Moreover, asymmetric effects on volatility have previously been discovered in stock markets. Hence, we also check the asymmetry effect on volatility of Bitcoin. Such effect on volatility refers to the phenomenon that a negative return will improve volatility on the next trading day.

The contribution of this study to existing literature is threefold. First, to the best of our knowledge, this is the first paper to examine the day-of-the-week effect on Bitcoin's volatility. Estimation results reveal that the day-of-the-week effect in return equation varies with sample period, whereas higher volatilities are observed on Monday and Thursday. Second, the day-of-the-week effect on both return and volatility cannot be explained by stock market returns (S&P500; SSEC; Nikkei 225) and foreign exchange market returns (USD/CNY; USD/JPY; EURO/USD). Third, no asymmetry effect on Bitcoin volatility is reported in this study.

The rest of the contents are organized as follows. Section 2 gives a literature review on the day-of-the-week effects in financial markets, and introduces some papers on Bitcoin. Section 3 describes the research methodology applied in this study. Section 4 presents data and some preliminary analysis. Section 5 provides results of empirical analysis. The final section provides a conclusion.

Section snippets

Literature review

There is an extending body of literature on the day-of-the-week effects on returns found in financial markets. Cross (1973) reported the significant difference between returns on Friday and Monday, and French (1980) found negative mean returns on Monday from S&P Composite Stock Index. Subsequent studies by Gibbons and Hess (1981), Keim and Stambaugh (1983), Rogalski (1984), and Smirlock and Starks (1986) verified the existence of day-of-the-week effect or weekend effect in the US stock markets.

Methodology

This study uses a similar methodology to that of Berument and Kiymaz (2001), but yet the time-varying variance is modeled with a Stochastic Volatility (hereafter, SV) model rather than a GARCH model. Both GARCH and SV models are usually employed to estimate volatility in financial econometrics, whereas the SV model is more flexible in its parameter constraints.

To begin with, we also check the presence of the day-of-the-week effect on return with a linear regression model using the following

Data and preliminary statistical tests

Data used here are daily prices calculated in USD for the Bitcoin Price Index (hereafter, BPI) from January 2013 to December 2018 collected from Coindesk. Daily prices of this Index are the average of Bitcoin prices across Bitcoin exchanges. Daily return in this study is defined as y_t = log(P_t/P_t−1) × 100, where P_t denotes the closing price on date t. Moreover, time standard of BPI is Coordinated Universal Time.

Fig. 1 shows the closing price and daily return in the upper plot and lower plot,

Day-of-the-week effect

Table 4 lists estimation results of linear model and two extended SV models. The column headed by ‘Mean’ lists the average values of parameters drawn from Bayesian sampling, while the column ‘Std. Dev’ presents standard deviation of the mean value. Two columns listed as ‘2.5%’ and ‘97.5%’ are 2.5% and 97.5% quantiles of posterior draws, namely 95% credible intervals. If the signs of two numbers are different, zero falls into this interval with 95% probability. Since all $\hat{R}$ are less than 1.1,

Conclusions

This study investigates the day-of-the-week effect on volatility and returns of Bitcoin from January 2013 to December 2018 using daily data obtained from the CoinDesk Bitcoin Price Index and extended SV models estimated through Bayesian MCMC sampling. Though Bitcoin is traded online every day, a day-of-the-week effect on Monday is detected as Décourt et al. (2017) and Caporale and Plastun (2018), which suggests significantly higher mean return than other weekdays. Our in-depth empirical

Acknowledgement

We thank editor(s) for valuable time, and we thank two anonymous reviewers for helpful comments. Donglian Ma gratefully acknowledges China Scholarship Council (CSC) for sponsoring the Ph.D. program at Osaka University. This research is supported by the Japan Society for the Promotion of Science, Grant-in-Aid for Scientific Research (C) 17K03657.

References (52)

D.G. Baur et al.
Bitcoin, gold and the US dollar – a replication and extension
Finan. Res. Lett.
(2018)
H. Berument et al.
Day of the week effect on foreign exchange market volatility: evidence from Turkey
Res. Int. Bus. Finan.
(2007)
E. Bouri et al.
On the hedge and safe haven properties of Bitcoin: is it really more than a diversifier?
Finan. Res. Lett.
(2017)
A. Charles
The day-of-the-week effects on the volatility: the role of the asymmetry
Eur. J. Oper. Res.
(2010)
M.M. Cornett et al.
Seasonalities and intraday return patterns in the foreign currency futures market
J. Bank. Finan.
(1995)
M. Dubois et al.
The day-of-the-week effect: the international evidence
J. Bank. Finan.
(1996)
A.H. Dyhrberg
Bitcoin, gold and the dollar – a GARCH volatility analysis
Finan. Res. Lett.
(2016)
A.H. Dyhrberg
Hedging capabilities of bitcoin. Is it the virtual gold?
Finan. Res. Lett.
(2016)
K.R. French
Stock returns and the weekend effect
J. Finan. Econ.
(1980)
D.A. Hsieh
The statistical properties of daily foreign exchange rates: 1974–1983
J. Int. Econ.
(1988)

P. Katsiampa

Volatility estimation for bitcoin: a comparison of GARCH models

Econ. Lett.

(2017)

M.C. Ke et al.

Day-of-the-week effect in the Taiwan foreign exchange market

J. Bank. Finan.

(2007)

H. Kiymaz et al.

The day of the week effect on stock market volatility and volume: international evidence

Rev. Finan. Econ.

(2003)

A. Phillip et al.

A new look at cryptocurrencies

Econ. Lett.

(2018)

M. Smirlock et al.

Day -of-the-weekend and intraday effect in stock returns

J. Finan. Econ.

(1986)

N. Yamori et al.

The day-of-the-week effect in foreign exchange markets: multi-currency evidence

Res. Int. Bus. Finan.

(2004)

J. Zhang et al.

The day-of-the-week effects of stock markets in different countries

Finan. Res. Lett.

(2017)

D.Y. Aharon et al.

Bitcoin and the day-of-the-week effect

Finan. Res. Lett.

(2018)

P. Alagidede

Day of the week seasonality in African stock markets

Appl. Finan. Econ. Lett.

(2008)

K. Aydogan et al.

Calendar anomalies in the Turkish foreign exchange markets

Appl. Finan. Econ.

(2003)

S.A. Basher et al.

Day-of-the-week effects in emerging stock markets

Appl. Econ. Lett.

(2006)

D.G. Baur et al.

Excess volatility as an impediment for a digital currency

SRRN Electron. J.

(2017)

M.H. Berument et al.

Stock market return and volatility: day-of-the-week effect

J. Econ. Finan.

(2012)

H. Berument et al.

The day of the week effect on stock market volatility

J. Econ. Finan.

(2001)

M. Betancourt

A Conceptual Introduction to Hamiltonian Monte Carlo

(2017)

J. Bouoiyour et al.

Bitcoin: a beginning of a new phase?

Econ. Bull.

(2016)

Cited by (37)

Predicting cryptocurrency market volatility: Novel evidence from climate policy uncertainty
2023, Finance Research Letters
This study employs two mixed-frequency volatility models to examine the impact of climate policy uncertainty on cryptocurrency price volatility. The empirical findings reveal that climate policy uncertainty has a significant positive impact on cryptocurrency price volatility and that this effect is mainly driven by extreme climate policy shocks. That is, abrupt and substantial shifts in climate policy lead to increased volatility in cryptocurrency prices. Moreover, different cryptocurrencies exhibit different responses to climate policy uncertainty. In addition, the predictive performance of the model that accounts for extreme shocks to climate policy uncertainty outperforms the basic GARCH-MIDAS-CPU model for all three cryptocurrencies.
Speculation or currency? Multi-scale analysis of cryptocurrencies—The case of Bitcoin
2023, International Review of Financial Analysis
This paper proposes a novel two-stage VMD-based multi-scale regression to analyze various cryptocurrency attributes that are still unclear in the existing literature. In the first stage, Variational Mode Decomposition (VMD) is used to decompose the cryptocurrency prices into low, medium and high frequency modes with different attributes. In the second stage, the VMD-based multi-scale regression is proposed for these modes with selected explanatory variables. Using the proposed framework, we focus on analyzing the multiple attributes of daily Bitcoin price data as a case study. Empirical results indicate that the low-frequency mode has specific currency or long-term investment characteristics, unlike the short/medium-term investment attributes for the medium-frequency mode, while the high-frequency mode represents some speculation. Some events merely affect a single frequency mode, but others impact all frequency modes. The results of events analysis based on VMD could enhance the identification of the multiple attributes of Bitcoin. Our findings are insightful for future regulation and management of virtual currencies.
Seasonal and Calendar Effects and the Price Efficiency of Cryptocurrencies
2022, Finance Research Letters
We investigate the pricing efficiency of numerous popular cryptocurrencies using a wide range of non-economic events that include calendar anomalies, natural condition-based anomalies, holidays when US exchanges are closed and secular and ethnic holidays when exchanges are open - all documented in the finance literature regarding equities. We document the existence of very few similar effects in the examined cryptocurrencies. Generally, anomalies found in Bitcoin do not hold for other cryptocurrencies and vice versa. The within-the-month effect is the only effect common to all cryptocurrencies. Our results have implications for efficient asset pricing and diversification benefits for these currencies.
The evolution of day-of-the-week and the implications in crude oil market
2022, Energy Economics
Citation Excerpt :
It has been found in various financial markets. These include the foreign exchange market (Ke et al., 2007), the Bitcoin market (Ma and Tanizaki, 2019; Aharon and Qadan, 2018), and the commodity futures markets (Qadan and Nama, 2018;). It is also found in the crude oil futures market (Qadan and Idilbi-Bayaa, 2021; Auer, 2014).
The movement of prices in the crude oil market are important to the international economy and financial asset returns. Day-of- the-week effect is a great challenge to the market's effectiveness. We examine the evolution of day-of-the-week and investigate its implications based on the West Texas Intermediate crude oil return from 14 May 2007 to 14 May 2021. We have obtained convincing findings that there is abnormal positive return on Wednesdays because the inventory shock schedule. Abnormal negative return on Mondays disappears sometimes, because bad sentiment is not the only decisive factor, as it is also determined by reactions to good sentiment. The results provide implication for the day-of-the-week effect and new evidence that crude oil market's efficiency changes over time. Policy makers, investors and producers can benefit from this.
The asset allocation utility of digital cryptocurrency
2022, Procedia Computer Science
In recent years, the digital cryptocurrency market has witnessed rapid development, but its asset allocation function has yet to be verified. In this paper, DCC-GARCH model is used to estimate the dynamic correlation between digital cryptocurrency and current mainstream assets, and the corresponding hedging effect of digital cryptocurrency is studied. Then, three mainstream asset allocation strategies are selected to analyze the risk and return of asset allocation portfolio after adding digital cryptocurrency, which verifies the asset allocation utility of digital cryptocurrency. This study can provide investment basis for investors and has certain theoretical and practical significance.
Forecasting volatility of Bitcoin
2022, Research in International Business and Finance
Citation Excerpt :
Since volatility of Bitcoin is a very important topic, several papers have investigated the impact of external shocks on Bitcoin volatility. These studies find that Bitcoin volatility is increased when geopolitical risks are high (Aysan et al., 2019), economic policy uncertainty is high (Wang et al., 2020), on days of cryptocurrency-related hacking attacks (Lyócsa and Molnár, 2016), and also Mondays and Thursdays (Ma and Tanizaki, 2019). Comovement among cryptocurrencies has been studied too (Beneki et al., 2019; Katsiampa, 2019).
Since Bitcoin price is highly volatile, forecasting its volatility is crucial for many applications, such as risk management or hedging. We study which model is the most suitable for forecasting Bitcoin volatility. We consider several GARCH and two heterogeneous autoregressive (HAR) models and compare them. Since we utilize realized variance estimated from high frequency data as a proxy for true volatility, we can draw sharper conclusions than studies which use only daily data. We find that EGARCH and APARCH perform best among the GARCH models. HAR models based on realized variance perform better than GARCH models based on daily data. Superiority of HAR models over GARCH models is strongest for short-term volatility forecasts.

View all citing articles on Scopus

View full text

The day-of-the-week effect on Bitcoin return and volatility

Abstract

Graphical abstract

Introduction

Section snippets

Literature review

Methodology

Data and preliminary statistical tests

Day-of-the-week effect

Conclusions

Acknowledgement

Finan. Res. Lett.

Res. Int. Bus. Finan.

Finan. Res. Lett.

Eur. J. Oper. Res.

J. Bank. Finan.

J. Bank. Finan.

Finan. Res. Lett.

Finan. Res. Lett.

J. Finan. Econ.

J. Int. Econ.

Econ. Lett.

J. Bank. Finan.

Rev. Finan. Econ.

Econ. Lett.

J. Finan. Econ.

Res. Int. Bus. Finan.

Finan. Res. Lett.

Bitcoin and the day-of-the-week effect

Finan. Res. Lett.

Day of the week seasonality in African stock markets

Appl. Finan. Econ. Lett.

Calendar anomalies in the Turkish foreign exchange markets

Appl. Finan. Econ.

Day-of-the-week effects in emerging stock markets

Appl. Econ. Lett.

Excess volatility as an impediment for a digital currency

SRRN Electron. J.

Stock market return and volatility: day-of-the-week effect

J. Econ. Finan.

The day of the week effect on stock market volatility

J. Econ. Finan.

A Conceptual Introduction to Hamiltonian Monte Carlo

Bitcoin: a beginning of a new phase?

Econ. Bull.