Search results

Rapid stock market growth without real economic back-up has led to the 2015 Chinese Stock Market Crash with thousands of stocks hitting the down limit simultaneously multiple times. The authors provide a detailed analysis of structural breaks in heavy-tailedness and asymmetry properties of returns in Chinese A-share markets due to the crash using recently proposed robust approaches to tail index inference. The empirical analysis points out to heavy-tailedness properties often implying possibly infinite second moments and also focuses on gain/loss asymmetry in the tails of daily returns on individual stocks. The authors further present an analysis of the main determinants of heavy-tailedness in Chinese financial markets. It points out to liquidity and company size as being the most important factors affecting the returns’ heavy-tailedness properties. At the same time, the authors do not observe statistically significant differences in tail indices of the returns on A-shares and the coefficients on factors affecting them in the pre-crisis and post-crisis periods.

The purpose of the paper is to back-test value-at-risk (VaR) models for conditional distributions belonging to a Generalized Hyperbolic (GH) family of Lévy processes – Variance Gamma, Normal Inverse Gaussian, Hyperbolic distribution and GH – and compare their risk-management features with a traditional unconditional extreme value (EV) approach using data from future contracts return data of S&P500, FTSE100, DAX, HangSeng and Nikkei 225 indices.

The authors apply tail-based and Lévy-based calibration to estimate the parameters of the models as part of the initial data analysis. While the authors utilize the peaks-over-threshold approach for generalized Pareto distribution, the conditional maximum likelihood method is followed in case of Lévy models. As the Lévy models do not have closed form expressions for VaR, the authors follow a bootstrap method to determine the VaR and the confidence intervals. Finally, for back-testing, they use both static calibration (on the entire data) and dynamic calibration (on a four-year rolling window) to test the unconditional, independence and conditional coverage hypotheses implemented with 95 and 99 per cent VaRs.

Both EV and Lévy models provide the authors with a conservative proportion of violation for VaR forecasts. A model targeting tail or fitting the entire distribution has little effect on either VaR calculation or a VaR model’s back-testing performance.

To the best of the authors’ knowledge, this is the first study to explore the back-testing performance of Lévy-based VaR models. The authors conduct various calibration and bootstrap techniques to test the unconditional, independence and conditional coverage hypotheses for the VaRs.

The last few years in the financial markets have shown great instability and high volatility. In order to capture the amount of risk a financial firm takes on in a single trading day, risk managers use a technology known as value‐at‐risk (VaR). There are many methodologies available to calculate VaR, and each has its limitations. Many past methods have included a normality assumption, which can often produce misleading figures as most financial returns are characterized by skewness (asymmetry) and leptokurtosis (fat‐tails). The purpose of this paper is to provide an overview of VaR and describe some of the most recent computational approaches.

This paper compares the Student‐t, autoregressive conditional heteroskedastic (ARCH) family of models, and extreme value theory (EVT) as a means of capturing the fat‐tailed nature of a returns distribution.

Recent research has utilized the third and fourth moments to estimate the shape index parameter of the tail. Other approaches, such as extreme value theory, focus on the extreme values to calculate the tail ends of a distribution. By highlighting benefits and limitations of the Student‐t, autoregressive conditional heteroskedastic (ARCH) family of models, and the extreme value theory, one can see that there is no one particular model that is best for computing VaR (although all of the models have proven to capture the fat‐tailed nature better than a normal distribution).

This paper details the basic advantages, disadvantages, and mathematics of current parametric methodologies used to assess value‐at‐risk (VaR), since accurate VaR measures reduce a firm's capital requirement and reassure creditors and investors of the firm's risk level.

The purpose of this paper is to discuss two important extensions to the well‐known value‐at‐risk (VaR) methodology, namely extreme value theory (EVT) and expected shortfall (ES). Both of these extensions address the weaknesses of VaR, in particular the methodology's tendency to systematically underestimate risk of extreme market events.

The theory of VaR and the two extensions are reviewed and the methodology is evaluated in light of the Basel II regulatory framework that calls for the use of VaR by financial institutions.

The paper clarifies the use of VaR and its extensions to make practitioners more aware of the pitfalls and how to address them. It is recommended that the two extended measures of extreme event risk (i.e. EVT and ES) be included into every risk manager's information pool.

A compact review of these approaches and their regulatory connection has not previously been compiled. This review is of particular value to risk managers and policy markers given the turbulent market conditions of the past year.

Asset pricing dynamics in a multi-asset framework when investors’ trading exhibits the disposition effect is studied. The purpose of this paper is to explore asset pricing dynamics and the switching behavior among multiple assets.

The dynamics of complex financial markets can be best explored by following agent-based modeling approach. The artificial financial market is populated with traders following two heterogeneous trading strategies: the technical and the fundamental trading rules. By simulation, the switching behavior among multiple assets is investigated.

The proposed framework can explain important stylized facts in financial time series, such as random walk price dynamics, bubbles and crashes, fat-tailed return distributions, absence of autocorrelation in raw returns, persistent long memory of volatility, excess volatility, volatility clustering and power-law tails. In addition, asset returns possess fractal structure and self-similarity features; though the switching behavior is only allowed among the asset markets.

The model demonstrates stylized facts of most real financial markets. Thereafter, the proposed model can serve as a testbed for policy makers, scholars and investors.

To the best of knowledge, no research has been conducted to introduce the disposition effect to a multi-asset agent-based model.

This paper aims at developing a behavioral agent-based model for interacting financial markets. Additionally, the effect of imposing Tobin taxes on market dynamics is explored.

The agent-based approach is followed to capture the highly complex, dynamic nature of financial markets. The model represents the interaction between two different financial markets located in two countries. The artificial markets are populated with heterogeneous, boundedly rational agents. There are two types of agents populating the markets; market makers and traders. Each time step, traders decide on which market to participate in and which trading strategy to follow. Traders can follow technical trading strategy, fundamental trading strategy or abstain from trading. The time-varying weight of each trading strategy depends on the current and past performance of this strategy. However, technical traders are loss-averse, where losses are perceived twice the equivalent gains. Market makers settle asset prices according to the net submitted orders.

The proposed framework can replicate important stylized facts observed empirically such as bubbles and crashes, excess volatility, clustered volatility, power-law tails, persistent autocorrelation in absolute returns and fractal structure.

Artificial models linking micro to macro behavior facilitate exploring the effect of different fiscal and monetary policies. The results of imposing Tobin taxes indicate that a small levy may raise government revenues without causing market distortion or instability.

This paper proposes a novel approach to explore the effect of loss aversion on the decision-making process in interacting financial markets framework.

Aims to investigate the accuracy of parametric, nonparametric, and semiparametric methods in predicting the one‐day‐ahead value‐at‐risk (VaR) measure in three types of markets (stock exchanges, commodities, and exchange rates), both for long and short trading positions.

The risk management techniques are designed to capture the main characteristics of asset returns, such as leptokurtosis and asymmetric distribution, volatility clustering, asymmetric relationship between stock returns and conditional variance, and power transformation of conditional variance.

Based on back‐testing measures and a loss function evaluation method, finds that the modeling of the main characteristics of asset returns produces the most accurate VaR forecasts. Especially for the high confidence levels, a risk manager must employ different volatility techniques in order to forecast accurately the VaR for the two trading positions.

Different models achieve accurate VaR forecasts for long and short trading positions, indicating to portfolio managers the significance of modeling separately the left and the right side of the distribution of returns.

The behavior of the risk management techniques is examined for both long and short VaR trading positions; to the best of one's knowledge, this is the first study that investigates the risk characteristics of three different financial markets simultaneously. Moreover, a two‐stage model selection is implemented in contrast with the most commonly used back‐testing procedures to identify a unique model. Finally, parametric, nonparametric, and semiparametric techniques are employed to investigate their performance in a unified environment.

This paper aims to capture tail dependence between sentiment index and Shanghai composite index (SCI) by proposing a sentiment index based on text mining.

Online text mining and the Copula model were used in this study.

First, the paper finds herding effect in the expression of investors’ sentiment from online text data, and the usage occurrence frequency of most vocabulary is less correlative with SCI. Second, given these two features, the paper uses weighted divide-and-conquer algorithm to construct a sentiment index. Finally, because of multivariate non-Gaussian joint distribution between them, the paper uses the Copula model to detect their tail dependences, and finds that both upper and lower tail dependences could have a significant influence between positive sentiment and SCI, with a higher probability on the upper one. Additionally, only the upper tail dependence exhibits the significant influence between negative sentiment and SCI.

This paper proposes a framework of constructing investment sentiment index with the weighted conquer-and-divide algorithm, and characterizes tail dependence between sentiment index and SCI. The implication can measure the environment of investment market of China and provide an empirical ground for bandwagon effect and bargain shopper effect.

Fat‐tailed distributions have been found in many financial and economic variables ranging from forecasting returns on financial assets to modeling recovery distributions in bankruptcies. They have also been found in numerous insurance applications such as catastrophic insurance claims and in value‐at‐risk measures employed by risk managers. Financial applications include: