Research background: In order to examine market uncertainty, the paper depicts broad patterns of risk and systematic exposure to global equity market shocks for the major South Asian and Chinese equity markets, as well as for specific assets (gold and Bitcoin). Purpose of the article: The purpose of this paper is to investigate the dynamic correlation among the major South Asian equity markets (India and Pakistan), the Chinese equity markets, the MSCI developed markets, Bitcoin, and gold markets. Methods: While applying the GARCH-Vine-Copula model and the TVP-VAR Connectedness approach, major patterns of dependency and interconnectedness between these markets are investigated. Findings & value added: We find that risk shocks from developed equity markets are critical in these dynamic links. A net return spillover from Bitcoin to the Chinese and Pakistani stock markets throughout the sample period is reported. Interestingly, gold can be applied to hedge and diversify positions in China and major South Asian markets, particularly following the COVID-19 outbreak. Our paper presents three main original add valued: (1) This paper adds global factors to the targeted study of risk transmission among South Asian and Chinese stock markets for the first time. (2)The assets of Bitcoin and gold were added to the study of risk transmission among South Asian and Chinese stock markets for the first time, enabling the research in this paper to observe the non-linear link among the South Asian and Chinese stock markets with them. (3) Our research adds to these lines of inquiry by giving empirical evidence on how COVID-19 altered the dependent structure and return spillover dynamics of Bitcoin, gold and South Asian and Chinese stock markets for the first time. Our results have critical implications for investors and policymakers to effectively understand the nature of market forces and develop risk-averse strategies.
The popularity of Bitcoin increased significantly in 2021. Bitcoin is considered to deliver high returns in a relatively short period, indicating that bitcoin has high volatility. Data with high volatility usually violates the Autoregresstive IntegratedinMovinginAverage (ARIMA)in homoscedasticity assumption. The Autoregressive Conditional Heteroscedasticity (ARCH) and General Autoregressive Conditional Heteroscedasticity (GARCH) model is often used to overcome the problem of heteroscedasticity in thelARIMA model. The ARCH and GARCH models canfbe used to model thefvolatilityfof data. This Research uses ARCH and GARCH models to overcome the heteroscedasticity problem caused by the high volatility of Bitcoin data for the period 30th June 2018 to 30th June 2022. The results of this study suggest that there might be a heteroscedasticity problem in Bitcoin data. The bestffiimodel for Bitcoin data ismiARIMA(1,0,[4])-GARCH(1,1) with an AIC value of -1,4263 at a 95% confidence level
Hohsuk Noh, Hyuna Jang, Kun Ho Kim, JongâMin Kim
This paper proposes a nonparametric directional dependence by using the local polynomial regression technique. With data generated from a bivariate copula having a nonmonotone regression structure, we show that our nonparametric directional dependence is superior to the copula directional dependence method in terms of the root-mean-square error. To validate the directional dependence with real data, we use the log returns of daily prices of Bitcoin, Ethereum, Ripple, and Stellar. We conclude that our nonparametric directional dependence, by using the local polynomial regression technique with asymmetric-threshold GARCH models for marginal distributions, detects the directional dependence better than the copula directional dependence method by an asymmetric GARCH model.
The cryptocurrency market is characterized by extremely high volatility. In the present study, we show the predictive ability of conditional EVT models in the cryptocurrency market during the price upsurge of 2020â2021. Taking high-frequency intraday data of four popular cryptocurrencies, Bitcoin, Ethereum, Litecoin, and Binance coin, we compare the accuracy of different competing models in estimating intraday value at risk (VaR) and expected shortfall (ES). The present study focuses on the extreme value theory (EVT) for modeling the tail of the distribution to forecast the measures of intraday VaR and ES. The study confirms the fat-tailed behavior of intraday returns of all four cryptocurrencies. Further, the study shows the magnitudes of high negative shocks are more than the positive ones for the returns of all four cryptocurrencies. The study uses suitable GARCH-family models such as apARCH, EGARCH, and CGARCH in the ARMA-GARCH framework. Using a two-stage approach the study shows how GARCH-EVT models with skewed studentâsâ t distribution outperform the predictability of conditional EVT with standard normal distribution as well as the unconditional EVT models in predicting intraday VaR and ES. The result of the study is useful for risk managers, day traders, and also for machine-based algorithmic trading.
Abstract This paper is motivated by Bitcoinâs rapid ascension into mainstream finance and recent evidence of a strong relationship between Bitcoin and US stock markets. It is also motivated by a lack of empirical studies on whether Bitcoin prices contain useful information for the volatility of US stock returns, particularly at the sectoral level of data. We specifically assess Bitcoin pricesâ ability to predict the volatility of US composite and sectoral stock indices using both in-sample and out-of-sample analyses over multiple forecast horizons, based on daily data from November 22, 2017, to December, 30, 2021. The findings show that Bitcoin prices have significant predictive power for US stock volatility, with an inverse relationship between Bitcoin prices and stock sector volatility. Regardless of the stock sectors or number of forecast horizons, the model that includes Bitcoin prices consistently outperforms the benchmark historical average model. These findings are independent of the volatility measure used. Using Bitcoin prices as a predictor yields higher economic gains. These findings emphasize the importance and utility of tracking Bitcoin prices when forecasting the volatility of US stock sectors, which is important for practitioners and policymakers.
In this study, the RiskMetrics method is used to estimate Value at Risk for two exchange rates: BitCoin/dollar and the South African Rand/dollar. Value at Risk is used to compare the riskiness of the two currencies. This is to help South Africans and investors understand the risk they are taking by converting their savings/investments to BitCoin instead of the South African currency, the Rand. The Maximum Likelihood Estimation method is used to estimate the parameters of the models. Seven statistical error distributions, namely Normal Distribution, skewed Normal Distribution, Studentâs T-Distribution, skewed Studentâs T-Distribution, Generalized Error Distribution, skewed Generalized Error Distribution, and the Generalized Hyperbolic Distributions, were considered when modelling and estimating model parameters. Value at Risk estimates suggest that the BitCoin/dollar return averaging 0.035 and 0.055 per dollar invested at 95% and 99%, respectively, is riskier than the Rand/dollar return averaging 0.012 and 0.019 per dollar invested at 95% and 99%, respectively. Using the Kupiec test, RiskMetrics with Generalized Error Distribution (p > 0.07) and skewed Generalized Error Distribution (p > 0.62) gave the best fitting model in the estimation of Value at Risk for BitCoin/dollar and Rand/dollar, respectively. The RiskMetrics approach seems to perform better at higher than lower confidence levels, as evidenced by higher p-values from backtesting using the Kupiec test at 99% than at 95% levels of significance. These findings are also helpful for risk managers in estimating adequate risk-based capital requirements for the two currencies.
Danai Likitratcharoen, Pan Chudasring, Chakrin Pinmanee, Karawan Wiwattanalamphong
In recent years, the cryptocurrency market has been experiencing extreme market stress due to unexpected extreme events such as the COVID-19 pandemic, the Russia and Ukraine war, monetary policy uncertainty, and a collapse in the speculative bubble of the cryptocurrencies market. These events cause cryptocurrencies to exhibit higher market risk. As a result, a risk model can lose its accuracy according to the rapid changes in risk levels. Value-at-risk (VaR) is a widely used risk measurement tool that can be applied to various types of assets. In this study, the efficacy of three value-at-risk (VaR) modelsânamely, Historical Simulation VaR, Delta Normal VaR, and Monte Carlo Simulation VaRâin predicting market stress in the cryptocurrency market was examined. The sample consisted of popular cryptocurrencies such as Bitcoin (BTC), Ethereum (ETH), Binance Coin (BNB), Cardano (ADA), and Ripple (XRP). Backtesting was performed using Kupiecâs POF test, Kupiecâs TUFF test, Independence test, and Christoffersenâs Interval Forecast test. The results indicate that the Historical Simulation VaR model was the most appropriate model for the cryptocurrency market, as it demonstrated the lowest rejections. Conversely, the Delta Normal VaR and Monte Carlo Simulation VaR models consistently overestimated risk at confidence levels of 95% and 90%, respectively. Despite these results, both models were found to exhibit comparable robustness to the Historical Simulation VaR model.
The paper examines whether an unanticipated event like the COVID-19 crisis has strengthened the contagion in the cryptocurrency market utilizing samples of data representing the pre-crisis and post-crisis periods. Employing the wavelet coherence and DCC-GARCH(1,1) models, we identify that the cryptocurrency market started integrating from 2018 as volatility within the market reduced. Our main finding is that the cryptocurrency market is highly interconnected and that the contagion strengthened during the crisis period. We draw appropriate policy implications from these findings.
The intensity of volatility persistence is sensitive to time scales, market returns and data regimes. Investors who acquire intangible digital assets in the form of "cryptocurrencies" should consider that they may or may not receive a fiat currency. Sometimes there is a possibility of a loss of the entire investment due to volatility of prices in digital currency/cryptocurrency. Several empirical studies are conducted to measure the volatility behavior of cryptocurrencies using different mathematical models like: i) Autoregressive Distributed Lag (ARDL) Model, ii) Heterogeneous Autoregressive (HAR) Model, iii) Autoregressive Conditional Heteroskedasticity (ARCH) Model, and iv) Generalized Autoregressive Conditional Heteroscedastic (GARCH) Models. This paper focuses on the review of various GARCH Models studied during 1980-2020.
The stochastic volatility (SV) model is one of the main methods of modeling time-varying volatility.In particular, SV model is actively used in estimation and prediction of financial market volatility and option pricing.This paper attempts to model the time-varying volatility of the bitcoin market price using SV model.Hidden Markov model (HMM) is combined with the SV model to capture characteristics of regime switching of the market.The HMM is useful for recognizing patterns of time series to divide the regime of market volatility.This study estimated the volatility of bitcoin by using data from Upbit, a cryptocurrency trading site, and analyzed it by dividing the volatility regime of the market to improve the performance of the SV model.The MCMC technique is used to estimate the parameters of the SV model, and the performance of the model is verified through evaluation criteria such as MAPE and MSE.
AntĂłnio Portugal Duarte, FĂĄtima Sol Murta, Nuno Baetas da Silva, Beatriz Rodrigues Vieira
This paper analysis and compares the volatility of seven cryptocurrencies â Bitcoin, Dogecoin, Ethereum, BitcoinCash, Ripple, Stellar and Litecoin â to the volatility of seven centralized currencies â Yuan, Yen, Canadian Dollar, Brazilian Real, Swiss Franc, Euro and British Pound. We estimate GARCH models to analyze their volatility. The results point to a considerably high volatility of cryptocurrencies when compared to that of centralized currencies. Therefore, we conclude that cryptocurrencies still fall far short of fulfilling all the requirements to be considered as a currency, specifically regarding the functions of store of value and unit of account.
This paper applies the multivariate GARCH models to investigate the role of Bitcoin as a hedge and safe haven for ASEAN+6 stock markets compared to gold. We used daily data for the dates 2 January 2017â20 January 2023, covering the recent COVID-19 pandemic. The empirical findings provide compelling evidence of cross-market shock and volatility transmission between stock returns and Bitcoin returns in both directions. Therefore, the dynamics of Bitcoin returns significantly influence the volatility of stock returns, and the relationship also holds in reverse. All diagonal element estimations are statistically significant for both periods, as shown by the findings of the return and volatility spillovers between the returns of gold and the ASEAN+6 stock market. For most ASEAN+6 equity markets evaluated, Bitcoin and gold are not safe havens, and their inclusion increases the portfolio downside risk.
Previous research has shown volatility jumps and co-jumping behaviours in cryptocurrency markets. Motivated by these findings, we employ the herding effect and financial contagion channel to outline a theoretical framework of volatility-state-dependent correlations in cryptocurrency markets. We show that digital currency markets are more strongly correlated when experiencing an identical volatility regime, which echoes co-jumping behaviours addressed by the literature. Moreover, the strong correlation that occurs when the paired cryptocurrencies simultaneously experience a high volatility regime results in the least effectiveness of diversification in terms of a minimum portfolio risk reduction. Last but not least, the proposed state-dependent approach in this study proves effective at the task of risk forecasting and risk reduction for cryptocurrency portfolios, beyond the bivariate GARCH-based models, which are a pure and simple time-dependent approach.
While volatility spillover is a vital research area in financial economics (due to its importance for risk valuation and portfolio diversification strategies), the volatility linkage between Bitcoin and electricity/energy markets has not received adequate attention. As the Bitcoin mining cost comes mainly from electricity (which is highly dependent on natural gas), we hypothesize that natural gas is a non-trivial Bitcoin price volatility driver and aim to test if this is the case. Specifically, we employ a widely used model called the HAR-RV model to assess volatility spillover across Bitcoin and natural gas using high-frequency data. We find a spillover effect from natural gas to Bitcoin, and the positive (negative) component of natural gas volatility stabilizes (destabilizes) Bitcoin volatility. The spillover effect is further examined and confirmed using an out-of-sample approach.
This study estimates the effects of the dual long memory property and structural breaks on the persistence level of six major cryptocurrency markets. We apply the Bai and Perron structural break test, InclĂĄn and Tiaoâs iterated cumulative sum of squares (ICSS) algorithm, and the fractionally integrated generalized autoregressive conditional heteroscedasticity (FIGARCH) model, with different distributions. The results show that long memory and structural breaks characterize the conditional volatility of cryptocurrency markets, confirming our hypothesis that ignoring structural breaks leads to an underestimation of the persistence of volatility modeling. The ARFIMA-FIGARCH model, with structural breaks and a skewed Student-t distribution, fits the cryptocurrency marketâs price dynamics well.
In this paper we develop a linear expectile hidden Markov model for the analysis of cryptocurrency time series in a risk management framework. The methodology proposed allows to focus on extreme returns and describe their temporal evolution by introducing in the model time-dependent coefficients evolving according to a latent discrete homogeneous Markov chain. As it is often used in the expectile literature, estimation of the model parameters is based on the asymmetric normal distribution. Maximum likelihood estimates are obtained via an Expectation-Maximization algorithm using efficient M-step update formulas for all parameters. We evaluate the introduced method with both artificial data under several experimental settings and real data investigating the relationship between daily Bitcoin returns and major world market indices.
In this paper, we investigate the co-dependence and portfolio value-at-risk of cryptocurrencies, with the Bitcoin, Ethereum, Litecoin and Ripple price series from January 2016 to December 2021, covering the crypto crash and pandemic period, using the generalized autoregressive score (GAS) model. We find evidence of strong dependence among the virtual currencies with a dynamic structure. The empirical analysis shows that the GAS model smoothly handles volatility and correlation changes, especially during more volatile periods in the markets. We perform a comprehensive comparison of out-of-sample probabilistic forecasts for a range of financial assets and backtests and the GAS model outperforms the classic DCC (dynamic conditional correlation) GARCH model and provides new insights into multivariate risk measures.
Abstract Mean-variance portfolio optimization models are sensitive to uncertainty in risk-return estimates, which may result in poor out-of-sample performance. In particular, the estimates may suffer when the number of assets considered is high and the length of the return time series is not sufficiently long. This is precisely the case in the cryptocurrency market, where there are hundreds of crypto assets that have been traded for a few years. We propose enhancing the mean-variance (MV) model with a pre-selection stage that uses a prototype-based clustering algorithm to reduce the number of crypto assets considered at each investment period. In the pre-selection stage, we run a prototype-based clustering algorithm where the assets are described by variables representing the profit-risk duality. The prototypes of the clustering partition are automatically examined and the one that best suits our risk-aversion preference is selected. We then run the MV portfolio optimization with the crypto assets of the selected cluster. The proposed approach is tested for a period of 17 months in the whole cryptocurrency market and two selections of the cryptocurrencies with the higher market capitalization (175 and 250 cryptos). We compare the results against three methods applied to the whole market: classic MV, risk parity, and hierarchical risk parity methods. We also compare our results with those from investing in the market index . The simulation results generally favor our proposal in terms of profit and risk-profit financial indicators. This result reaffirms the convenience of using machine learning methods to guide financial investments in complex and highly-volatile environments such as the cryptocurrency market.
Although cryptocurrencies are catching the fancy of investors for various benefits such as decentralization, low transaction costs, and inflation hedging, their extreme volatility is sometimes keeping many away. Consequently, modeling and forecasting cryptocurrency market volatility are essential to investorsâ investment decisions and risk management. However, most previous studies have been limited to Bitcoin volatility, disregarding cryptocurrency market performance as a whole. This study estimates realized volatility of cryptocurrency market with a variety of algorithms employing a portfolio-style technique. After comparison, LSTM networks surpass the conventional GARCH-type models; meanwhile, the hybrid GARCH neural network models perform the worst. This study provides an impetus for a significant number of academics interested in the extreme volatility of cryptocurrencies. Additionally, it illustrates that more sophisticated models may not always lead to better predictive performance.
Minhyuk Lee, Younghwan Cho, Seung Eun Ock, Jae Wook Song
This research analyzes asymmetric volatility and multifractality in four representative cryptocurrencies using index-based asymmetric multifractal detrended fluctuation analysis. We suggest investigating an idiosyncratic risk premium, which can be obtained by removing the market influence in the cryptocurrency return series. We call the process a capital asset pricing model filter. The analyses on the original return series showed no significant sign of asymmetric volatility. However, the filter revealed a distinct asymmetric volatility, distinguishing the uptrend and downtrend fluctuations. Furthermore, the analyses on the idiosyncratic risk premium detected some cases of asymmetry in the degree and source of multifractality, whereas that on the original return series failed to detect the asymmetry. In conclusion, in a highly volatile market, the capital asset pricing model filter can improve an investigation of the asymmetric multifractality in cryptocurrencies.
Dora Almeida, Andreia DionĂsio, Isabel Vieira, Paulo Ferreira
Cryptocurrencies are relatively new and innovative financial assets. They are a topic of interest to investors and academics due to their distinctive features. Whether financial or not, extraordinary events are one of the biggest challenges facing financial markets. The onset of the COVID-19 pandemic crisis, considered by some authors a "black swan", is one of these events. In this study, we assess integration and contagion in the cryptocurrency market in the COVID-19 pandemic context, using two entropy-based measures: mutual information and transfer entropy. Both methodologies reveal that cryptocurrencies exhibit mixed levels of integration before and after the onset of the pandemic. Cryptocurrencies displaying higher integration before the event experienced a decline in such link after the world became aware of the first cases of pneumonia in Wuhan city. In what concerns contagion, mutual information provided evidence of its presence solely for the Huobi Token, and the transfer entropy analysis pointed out Tether and Huobi Token as its main source. As both analyses indicate no contagion from the pandemic turmoil to these financial assets, cryptocurrencies may be good investment options in case of real global shocks, such as the one provoked by the COVID-19 outbreak.
ABSTRACT Recent literature explores the profitability of various cryptocurrency momentum trading strategies and proposes cryptocurrency momentum as a pricing factor (Liu et al.). How risky is this factorâbased investment strategy for cryptoâinvestments? We answer this question by examining the distributional characteristics (hence, riskiness) of six cryptocurrency momentum trading strategies. The empirical evidence suggests that the realised variances of cryptocurrency momentum strategies are governed by power laws. The statistical tests derived from block bootstraps indicate that the population mean and variance of the momentum factor realised variances are statistically not defined. Contrary to the belief that cryptocurrency momentum trading strategies produce generous payoffs, our results imply that, in real life, we might not be able to realise these risk premiums. We conclude that the performance metrics evaluating the profitability of cryptocurrency momentum strategies, using variance as an input, are not informative. We also find crossâsectional dependence amongst the tail risk of momentum strategies based on different formation periods.