Lili Matic, Natalie Packham, Wolfgang Karl HĂ€rdle
The cryptocurrency market is volatile, non-stationary and non-continuous. Together with liquid derivatives markets, this poses a unique opportunity to study risk management, especially the hedging of options, in a turbulent market. We study the hedge behaviour and effectiveness for the class of affine jump diffusion models and infinite activity Levy processes. First, market data is calibrated to stochastic volatility inspired (SVI)-implied volatility surfaces to price options. To cover a wide range of market dynamics, we generate Monte Carlo price paths using an SVCJ model (stochastic volatility with correlated jumps), a close-to-actual-market GARCH-filtered kernel density estimation as well as a historical backtest. In all three settings, options are dynamically hedged with Delta, Delta-Gamma, Delta-Vega and Minimum Variance strategies. Including a wide range of market models allows to understand the trade-off in the hedge performance between complete, but overly parsimonious models, and more complex, but incomplete models. The calibration results reveal a strong indication for stochastic volatility, low jump frequency and evidence of infinite activity. Short-dated options are less sensitive to volatility or Gamma hedges. For longer-dated options, tail risk is consistently reduced by multiple-instrument hedges, in particular by employing complete market models with stochastic volatility.
The salience theory of choice under risk shows that investor behavior drives cross-sectional cryptocurrency returns. Investors place too much weight on salient payouts, causing overvaluation of cryptocurrencies with upward salience returns and undervaluation of those with downward salience returns, leading to negative expected returns for the former and positive expected returns for the latter. The salience effect in the cryptocurrency market is more pronounced than in equity markets, making it a significant risk factor for explaining other cross-sectional returns in the cryptocurrency market. Unlike other documented return predictors, the salience theory uniquely contributes to understanding the cryptocurrency market. Video Abstract: https://youtu.be/F8BxhDWW7b4.
Many models have been developed to model, estimate and forecast financial time series volatility, amongst which are the most popular autoregressive conditional heteroscedasticity (ARCH) model introduced by Engle (1982) and generalized autoregressive conditional heteroscedasticity (GARCH) model introduced by Bollerslev (1986). The aim of this paper is to determine which type of ARCH/GARCH models can fit the best following cryptocurrencies: Ethereum, Neo, Ripple, Litecoin, Dash, Zcash and Dogecoin. It is found that the EGARCH model is the best fitted model for Ethereum, Zcash and Neo, PARCH model is the best fitted model for Ripple, while for Litecoin, Dash and Dogecoin it depends on the selected distribution and information criterion.
Lingling Qian, Yuexiang Jiang, Huaigang Long, RUOYI SONG
We are the first to explore the effect of economic policy uncertainty (EPU) and the COVID-19 pandemic on the correlation between the cryptocurrency index CRIX and the world stock market portfolio, as well as the hedging properties of CRIX. To this end, we mainly apply the dynamic conditional correlation model with mixed data sampling regressions, a threshold vector autoregressive model and the generalized impulse response function. We demonstrate that the correlation is influenced by the uncertainty stance of the economy and behaves differently in low-, medium- and high-uncertainty periods. Most of the abnormal market relations exist in high levels of EPU or during the COVID-19 period, and the impact of global EPU is greater than that of EPU originating in the United States, Europe, Russia and China. Moreover, the CRIX can serve as a hedge asset against the world stock market. The high (low) level of EPU has a significantly positive (negative) effect on the optimal hedge ratio of CRIX, which increases significantly during the COVID-19 period. Our findings have implications for risk management, portfolio allocations and hedging strategies.
Calendar anomalies as the seasonal tendencies in stock returns are the signal of irregular behaviour of stock markets. These anomalies have been comprehensively studied in many matured as well as emerging stock markets. But there is lack of exploration of calendar anomalies in the cryptocurrency market. So, the present treatise is an attempt to fill this lacuna by studying day of the week effect on cryptocurrencies' returns and volatility. This study is based on the prices of eight cryptocurrencies (viz. Bitcoin, EOS, Ethereum, Bitcoin Cash, Litecoin, Tether, XRP and Stellar) for a period starting from July 2017 and up to March 2020. The series of daily and day-wise returns were initially studied for stationarity using Ng-Perron tests and augmented DickeyâFuller test. The results from these tests confirmed that the cryptocurrencies' return series are stationary. The day of the week effect on cryptocurrencies returns was studied by introducing the dummies for each day of the week in the ordinary least square regression equation. The residuals from the ordinary least square regression equation were tested for ARCH effect using Engle's ARCH test. The results from the test confirmed the presence of ARCH effect in all series. The GARCH (1,1) model and PARCH model were further applied to account for ARCH effect and these models confirmed the presence of the day of the week effect in all the cryptocurrencies' returns and volatility except for day of week effect in Bitcoin and Tether returns. So, the significant day of the week effect was present in all cryptocurrencies' returns and volatility but the significant day of the week effect was absent in Bitcoin's returns and Tether's returns. These findings of significant day effect may help the existing and potential investors in taking investment decision in contemporary scenario of no ban in cryptocurrency market in India.
AyĆe MetiÌn KarakaĆ, Aslıhan DEMÄ°R, Sinan Ăalık
In recent years, there has been a growing interest on the combination of copulas with mixture model. The combination of vine copulas incorporated into a finite mixture model is also helpful to capture secret structures in a data. This paper aims to examine the relationship between bitcoin and other crypto money indicators with the CD Vine Copula Approach method. In the study, we use closing prices of Bitcoin, Bitcoin Cash, Ethereum, Litecoin, and IOT. The results show that there is a strong dependence between bitcoin and prominent financial indicators.
Risk in finance may come from (negative) asset returns whilst payment loss is a typical risk in insurance. It is often that we encounter several risks, in practice, instead of single risk. In this paper, we construct a dependence modeling for financial risks and form a portfolio risk of cryptocurrencies. The marginal risk model is assumed to follow a heteroscedastic process of GARCH(1,1) model. The dependence structure is presented through vine copula. We carry out numerical analysis of cryptocurrencies returns and compute Value-at-Risk (VaR) forecast along with its accuracy assessed through different backtesting methods. It is found that the VaR forecast of returns, by considering vine copula-based dependence among different returns, has higher forecast accuracy than that of returns under prefect dependence assumption as benchmark. In addition, through vine copula, the aggregate VaR forecast has not only lower value but also higher accuracy than the simple sum of individual VaR forecasts. This shows that vine copula-based forecasting procedure not only performs better but also provides a well-diversified portfolio.
Using daily data of the 100 largest cryptocurrencies, we construct the efficient sorting portfolios and the quantile-based sorting portfolios based on ten factors. We find two price factors that can well predict cryptocurrency returns. The efficient sorting portfolios outperform the traditional quantile-based portfolios and the naive 1/N portfolios. The outperformance is largely due to the use of DCC-NL estimator, which captures the dynamic of covariance matrix and meanwhile addresses the curse of dimensionality. In addition, leverage constraints are important for cryptocurrency portfolios to control their risks.
This paper analyzes high-frequency estimates of good and bad realized volatility of Bitcoin. We show that volatility asymmetry depends on the volatility regime and the forecast horizon. For one-day ahead forecasts, good volatility commands a stronger impact on future volatility than bad volatility on average and in extreme volatility regimes but not across all quantiles and volatility regimes. For 7-day ahead forecasting horizons the asymmetry is similar to that observed in stock markets and becomes stronger with increasing volatility. Compared with stock markets, the persistence and predictability of volatility is low indicating high variations of volatility.
The present study is on the five cryptocurrency daily mean return time series linearity dynamics during the Covid-19 period. These cryptocurrencies were chosen based on their influence on the market, primarily driven by its market capitalisation. Tether is included as the most important stable coin on the market, nominally pegged to the U.S. dollar (USD). The reason to investigate it is that there are some inconsistencies in its behaviour as opposed to the other four cryptocurrencies. This study found that the behaviour of Tether cryptocurrency daily average return time series pattern is highly nonlinear and chaotic in nature, whereas the other four cryptocurrencies (namely Bitcoin, Ethereum, XRP and Bitcoin Cash) daily average return time series were found to be linear in nature. To further study Tether’s nonlinear time series rich dynamics, this study deployed one category of the regime switching models popularly known as the threshold regressions. The study estimates fairly suggest that both the threshold autoregression (TAR) and smooth transition autoregressive (STAR) models with lag 1 are adequate to capture the rich nonlinear and chaotic dynamics of Tether’s daily average return time series.
This paper investigates asymmetry and local leverage behaviour in individual and aggregate markets of leading cryptocurrencies, and compares such characteristics to diverse traditional emerging asset classes. Generally different from the cryptocurrencies, the results show diffuse evidence of asymmetry and a significant presence of local leverage in the emerging markets. New findings indicate that megaâsize cryptocurrencies like Bitcoin and Ripple exhibit returnâvolatility behaviour whereby volatility changes in their markets increase rather by a response to positive shocks than by a response to negative shocks. Akin to safe net assets, particularly gold, the inverse asymmetric reactions of the cryptocurrency markets position them distinctively from the existing emerging markets, suggestive that the digital assets stand to offer potentials beyond being diversifiers.
This paper aims to enrich the understanding and modelling strategies for cryptocurrency markets by investigating major cryptocurrenciesâ returns determinants and forecast their returns. To handle model uncertainty when modelling cryptocurrencies, we conduct model selection for an autoregressive distributed lag (ARDL) model using several popular penalized least squares estimators to explain the cryptocurrenciesâ returns. We further introduce a novel model averaging approach or the shrinkage Mallows model averaging (SMMA) estimator for forecasting. First, we find that the returns for most cryptocurrencies are sensitive to volatilities from major financial markets. The returns are also prone to the changes in gold prices and the Forex marketâs current and lagged information. Then, when forecasting cryptocurrenciesâ returns, we further find that an ARDL(p,q) model estimated by the SMMA estimator outperforms the competing estimators and models out-of-sample.
Abstract Through the application of the VAR-AGARCH model to intra-day data for three cryptocurrencies (Bitcoin, Ethereum, and Litecoin), this study examines the return and volatility spillover between these cryptocurrencies during the pre-COVID-19 period and the COVID-19 period. We also estimate the optimal weights, hedge ratios, and hedging effectiveness during both sample periods. We find that the return spillovers vary across the two periods for the Bitcoin-Ethereum, Bitcoin-Litecoin, and Ethereum-Litecoin pairs. However, the volatility transmissions are found to be different during the two sample periods for the Bitcoin-Ethereum and Bitcoin-Litecoin pairs. The constant conditional correlations between all pairs of cryptocurrencies are observed to be higher during the COVID-19 period compared to the pre-COVID-19 period. Based on optimal weights, investors are advised to decrease their investments (a) in Bitcoin for the portfolios of Bitcoin/Ethereum and Bitcoin/Litecoin and (b) in Ethereum for the portfolios of Ethereum/Litecoin during the COVID-19 period. All hedge ratios are found to be higher during the COVID-19 period, implying a higher hedging cost compared to the pre-COVID-19 period. Last, the hedging effectiveness is higher during the COVID-19 period compared to the pre-COVID-19 period. Overall, these findings provide useful information to portfolio managers and policymakers regarding portfolio diversification, hedging, forecasting, and risk management.
In this paper, we consider a variety of multi-state Hidden Markov models for predicting and explaining the Bitcoin, Ether and Ripple returns in the presence of state (regime) dynamics. In addition, we examine the effects of several financial, economic and cryptocurrency specific predictors on the cryptocurrency return series. Our results indicate that the Non-Homogeneous Hidden Markov (NHHM) model with four states has the best one-step-ahead forecasting performance among all competing models for all three series. The dominance of the predictive densities over the single regime random walk model relies on the fact that the states capture alternating periods with distinct return characteristics. In particular, the four state NHHM model distinguishes bull, bear and calm regimes for the Bitcoin series, and periods with different profit and risk magnitudes for the Ether and Ripple series. Also, conditionally on the hidden states, it identifies predictors with different linear and non-linear effects on the cryptocurrency returns. These empirical findings provide important insight for portfolio management and policy implementation.
Diese Masterarbeit greift die Theorie der Portfoliooptimierung auf: die mathematische Formulierung des Problems, seine Ableitungen (Risikominimierungsformulierung) und Annahmen, seine EinschrÀnkungen sowie einige Verbesserungen und Erweiterungen des bestehenden Frameworks. Ziel der Arbeit ist es auch, in Python zu simulieren und zu implementieren: Markowitz (Global Varianzminimal, Maximum Sharpe), Hierarchical Risk Parity und drei naiv Portfolios: gleichgewichtete, inverse VolatilitÀt und inverse Varianz in der neuartigen Anlageklasse der KryptowÀhrungen. Als Benchmark wird die CRyptocurrency IndeX, CRIX, verwendet. Die Portfoliooptimierung wird anhand von 120 Tagen tÀglicher historischer Daten berechnet, wobei die Portfolio-Anpassung alle 7 Tage und 30 Tage erfolgt. Portfolios sind Long-Short Strategien ohne Hebelwirkung und Verbesserungen in der Kovarianzmatrix werden mithilfe von Eigenwert-Clipping der Zufallsmatrixtheorie angewendet.
Maria Letizia Guerra, Laerte Sorini, Luciano Stefanini
Sentiment analysis to characterize the properties of Bitcoin prices and their forecasting is here developed thanks to the capability of the Fuzzy Transform (F-transform for short) to capture stylized facts and mutual connections between time series with different natures. The recently proposed Lp-norm F-transform is a powerful and flexible methodology for data analysis, non-parametric smoothing and for fitting and forecasting. Its capabilities are illustrated by empirical analyses concerning Bitcoin prices and Google Trend scores (six years of daily data): we apply the (inverse) F-transform to both time series and, using clustering techniques, we identify stylized facts for Bitcoin prices, based on (local) smoothing and fitting F-transform, and we study their time evolution in terms of a transition matrix. Finally, we examine the dependence of Bitcoin prices on Google Trend scores and we estimate short-term forecasting models; the DieboldâMariano (DM) test statistics, applied for their significance, shows that sentiment analysis is useful in short-term forecasting of Bitcoin cryptocurrency.
Oct 26, 2020·CEUR Workshop Proceedings, Vol-2713: Proceedings of the Selected Papers of the Special Edition of International Conference on Monitoring, Modeling & Management of Emergent Economy (M3E2-MLPEED 2020)
Current research has led to a rejection of the hypothesis of a normal distribution of financial assets returns. Under these conditions, portfolio variance cannot serve as a good risk measure. In this paper analyzed the daily returns of the most common cryptocurrencies: Bitcoin, Ethereum, XRP, USDT, Bitcoin Cash, Litecoin. It is shown that the asset returns are not normally distributed, but with good precision follow the Cauchy distribution and Laplace distribution. The analytical expressions for risk measure were obtained using the distribution function and the VaR technique. However, the risk assessment of the return obtained on the basis of the Cauchy distribution is twice as high as the risk assessment obtained on the basis of the Laplace distribution. Therefore, the question arises: what distribution law to use to measurement the cryptocurrency risk? The paper shows that the Laplace distribution is the most adequate basis for measuring of cryptocurrencies risk.
This paper examines the relationship of the leading financial assets, Bitcoin, Gold, and S&P 500 with GARCH-Dynamic Conditional Correlation (DCC), Nonlinear Asymmetric GARCH DCC (NA-DCC), Gaussian copula-based GARCH-DCC (GC-DCC), and Gaussian copula-based Nonlinear Asymmetric-DCC (GCNA-DCC). Under the high volatility financial situation such as the COVID-19 pandemic occurrence, there exist a computation difficulty to use the traditional DCC method to the selected cryptocurrencies. To solve this limitation, GC-DCC and GCNA-DCC are applied to investigate the time-varying relationship among Bitcoin, Gold, and S&P 500. In terms of log-likelihood, we show that GC-DCC and GCNA-DCC are better models than DCC and NA-DCC to show relationship of Bitcoin with Gold and S&P 500. We also consider the relationships among time-varying conditional correlation with Bitcoin volatility, and S&P 500 volatility by a Gaussian Copula Marginal Regression (GCMR) model. The empirical findings show that S&P 500 and Gold price are statistically significant to Bitcoin in terms of log-return and volatility.
The semi-nonparametric (SNP) modeling of the return distribution has been proved to be a flexible and accurate methodology for portfolio risk management that allows two-step estimation of the dynamic conditional correlation (DCC) matrix. For this SNP-DCC model, we propose a stepwise procedure to compute pairwise conditional correlations under bivariate marginal SNP distributions, overcoming the curse of dimensionality. The procedure is compared to the assumption of Dynamic Equicorrelation (DECO), which is a parsimonious model when correlations among the assets are not significantly different but requires joint estimation of the multivariate SNP model. The risk assessment of both methodologies is tested for a portfolio on cryptocurrencies by implementing backtesting techniques and for different risk measures: Value-at-Risk, Expected Shortfall and Median Shortfall. The results support our proposal showing that the SNP-DCC model has better performance for a smaller confidence level than the SNP-DECO model, although both models perform similarly for higher confidence levels.