投资组合动态VaR风险度量

投资组合的VaR风险度量依赖于投资组合中金融资产间联合分布函数的确定，随着投资组合规模的扩大，其VaR的计算难度也不断加大。利用ICA可以将多元联合概率分布函数转化为一元概率分布函数乘积实现简化计算的特点，基于ICA的投资组合动态VaR风险度量方法和计算步骤，克服了多元非正态条件下VaR测算上的困难。实证研究表明，与EWMA模型法、MGARCH模型法相比，ICA法能够准确地度量投资组合动态VaR。     

我国证券市场的风险度量

金融资产收益率序列具有典型的尖峰厚尾特征,影响着人们对极端事件的判断与预测,这种现象已引起越来越多学者的重视,而描述这种特性需以合适的概率分布函数为基础,因此,寻求更好的概率分布函数对风险度量具有十分重要的意义,文章将广义双曲线分布及其子类应用到中国证券市场,采用VaR、ES和Omega三个风险度量指标计算其尾部特征,得到了较好的拟合结果.     

金融控股公司的风险度量

混业经营是一种趋势,金融控股公司的风险度量已是一个难题。本文运用VaR和Copulas函数等方法构建计算混业经营金融控股公司的风险度量模型Copula-VaR,对金融控股公司混业经营风险进行度量;并对几种风险度量VaR方法进行了比较,得出多样化经营的优势。     

基于遗传算法的上证指数一致性风险动态度量方法

一、引言 继VaR之后,一致性风险度量已成为金融风险领域一个新的研究热点.一致性风险度量之一的谱风险测度,包括了迄今所提出的几乎所有的一致性风险度量(CVaR、ES等).与VaR、ES相比,目前关于谱风险测度的计算方法较少,如样本情形下的离散计算方法、功能函数法等,然而,这些都是静态分析方法.     

基于广义双曲线SV模型的极值风险度量研究

在金融风险的度量中,拟合分布的选取直接影响到风险度量的精度问题。针对金融收益序列的动态变化,在SV模型中引入广义双曲线学生偏t分布(SV-GHSKt)拟合金融收益序列的尖峰厚尾、不对称以及杠杆效应等特征,通过马尔科夫蒙特卡洛模拟的方法将收益率序列转化为标准残差序列,然后用极值理论的POT模型拟合标准残差序列尾部分布,进而建立一种新的金融风险度量模型———基于SV-GHSKt-POT的动态VaR模型。用该模型对上证综合指数做实证研究,结果表明,SV-GHSKt-POT的动态VaR模型能很好地模拟金融收益序列的尖峰厚尾性、波动集聚性及杠杆效应,并且能够合理有效地提高风险测度的精度,尤其在高的置信水平下表现更好。     

基于GARCH模型的CVaR信贷风险度量方法研究

文章针对VaR方法不是一致性度量,不满足凸性,尤其是该模型不能体现尾部事件发生时其可能损失的程度等一系列缺陷;同时针对金融时间序列具有偏性和尖峰厚尾两大特性,用修正的VaR方法——基于GARCH模型的CVaR方法来度量风险。该方法的优点在于可以反映出损失超过VaR时可能遭受的平均潜在损失的大小,解决了VaR方法无法进一步识别风险是可以忍受的还是灾难性的问题,弥补了VaR不能反映损失尾部信息的缺陷,能够防范小概率极端金融风险,降低了银行发生灾难性风险的可能性。     

金融市场风险度量方法的对比分析

金融市场风险度量在金融风险管理中扮演着重要角色,当前广为流行的两个金融风险度量工具为VaR和ES,其计算方法有多种.文章以中国股市数据为例,对几种计算方法的准确性和有效性进行了比较分析.通过实证分析,我们发现:RiskMetrics方法不太适用中国的股票市场,EVT方法虽然具有准确性但是有效性不足.这些方法之中仅MGARCH-BEKK方法能很好地解释中国股票市场风险特征,这是由于该方法能够更为准确地把握中国沪深股市之间的波动性和时变相关性.     

VaR方法在我国银行风险管理中的应用

VaR方法是目前国际上金融风险管理的主流方法之一,它利用数学工具计算金融市场的风险,可以有效规避市场风险,在金融领域中有着广泛应用.把VaR法引入我国的银行风险管理领域,对于我国的金融市场建设有着重大的现实意义.     

中国股市动态VaR计量模型分析

风险测量是现代金融活动的中心。近年来,新兴的VaR测量方法已成为国际上风险管理的主流方法。文章介绍了利用GARCH模型的VaR计算方法,并比较了基于不同分布假设的4种GARCH模型计算的VaR值,并得出以下结论:证券市场收益率具有强烈的GARCH效应和非正态分布性;基于GARCH-T的VaR估计值在给定的显著性水平下能够有效地度量金融资产的风险。     

BMM模型在商业银行操作风险度量中的应用

文章利用极值理论中的BMM模型对商业银行操作风险损失极端值分布进行估计,采用广义极值分布构建VaR模型,组建极值数据组,运用极大似然估计法估计两个参数,进而计算操作风险损失VaR。最后结合我国商业银行1994~2008年的220个操作风险损失数据进行实证研究,结果显示BMM模型具有超越样本的估计能力,在数据较少条件下能得到较准确结果,用其度量商业银行的操作风险损失VaR是合理的,这为我国商业银行操作风险度量和管理提供一定的量化依据。     

基于尾部指数回归方法的CVaR估计以及实证研究

 在险价值VaR是一种非常重要的金融风险度量方法,近期也有很多关于动态VaR以及条件VaR (CVaR) 等方面的研究。根据金融资产的收益率具有重尾特征这一事实,本文假定金融资产收益率服从重尾分布,并假定重尾分布的尾部指数随着收益率发生变化。本文基于尾部指数回归模型对重尾分布的尾部指数进行估计,进而得到收益率尾部数据所服从的条件分布,并首次运用该方法对条件VaR进行估计。本文对沪深300指数进行了实证研究,得到CVaR的估计,并对估计得到的CVaR的预测效果作出检验,并与传统VaR估计方法进行了对比,实证结果发现本文的方法的预测效果更好。     

The generalized Gudermannian distribution: inference and volatility modelling

In this paper, we introduce a new distribution, called generalized Gudermannian (GG) distribution, and its skew extension for GARCH models in modelling daily Value-at-Risk (VaR). Basic structural properties of the proposed distribution are obtained including probability density and cumulative distribution functions, moments, and stochastic representation. The maximum likelihood method is used to estimate unknown parameters of the proposed model and finite sample performance of maximum likelihood estimates are evaluated by means of Monte-Carlo simulation study. The real data application on Nikkei 225 index is given to demonstrate the performance of GARCH model specified under skew extension of GG innovation distribution against normal, Student's-t, skew normal and generalized error and skew generalized error distributions in terms of the accuracy of VaR forecasts. The empirical results show that the GARCH model with GG innovation distribution produces the most accurate VaR forecasts for all confidence levels.     

A quasi-Bayesian model averaging approach for conditional quantile models

The value at risk (VaR) is a risk measure that is widely used by financial institutions to allocate risk. VaR forecast estimation involves the evaluation of conditional quantiles based on the currently available information. Recent advances in VaR evaluation incorporate conditional variance into the quantile estimation, which yields the conditional autoregressive VaR (CAViaR) models. However, uncertainty with regard to model selection in CAViaR model estimators raises the issue of identifying the better quantile predictor via averaging. In this study, we propose a quasi-Bayesian model averaging method that generates combinations of conditional VaR estimators based on single CAViaR models. This approach provides us a basis for comparing single CAViaR models against averaged ones for their ability to forecast VaR. We illustrate this method using simulated and financial daily return data series. The results demonstrate significant findings with regard to the use of averaged conditional VaR estimates when forecasting quantile risk.     

Production Frontiers and Panel Data

Value at risk (VaR) is the standard measure of market risk used by financial institutions. Interpreting the VaR as the quantile of future portfolio values conditional on current information, the conditional autoregressive value at risk (CAViaR) model specifies the evolution of the quantile over time using an autoregressive process and estimates the parameters with regression quantiles. Utilizing the criterion that each period the probability of exceeding the VaR must be independent of all the past information, we introduce a new test of model adequacy, the dynamic quantile test. Applications to real data provide empirical support to this methodology.     

A dynamic double asymmetric copula generalized autoregressive conditional heteroskedasticity model: application to China's and US stock market

Modeling the relationship between multiple financial markets has had a great deal of attention in both literature and real-life applications. One state-of-the-art technique is that the individual financial market is modeled by generalized autoregressive conditional heteroskedasticity (GARCH) process, while market dependence is modeled by copula, e.g. dynamic asymmetric copula-GARCH. As an extension, we propose a dynamic double asymmetric copula (DDAC)-GARCH model to allow for the joint asymmetry caused by the negative shocks as well as by the copula model. Furthermore, our model adopts a more intuitive way of constructing the sample correlation matrix. Our new model yet satisfies the positive-definite condition as found in dynamic conditional correlation-GARCH and constant conditional correlation-GARCH models. The simulation study shows the performance of the maximum likelihood estimate for DDAC-GARCH model. As a case study, we apply this model to examine the dependence between China and US stock markets since 1990s. We conduct a series of likelihood ratio test tests that demonstrate our extension (dynamic double joint asymmetry) is adequate in dynamic dependence modeling. Also, we propose a simulation method involving the DDAC-GARCH model to estimate value at risk (VaR) of a portfolio. Our study shows that the proposed method depicts VaR much better than well-established variance–covariance method.     

金融风险度量VaR与CVaR方法的比较研究及应用

风险价值(VaR)是近年来受到国际金融界的广泛支持和认可的一种度量金融风险的工具。文章指出了风险价值(VaR)模型两个重大的缺陷,并对它和条件风险价值(CVaR)金融风险度量模型进行了详细的介绍和对比分析,给出了它们的共同点和CVaR在投资组合应用中的优势,结合中国金融市场的实际情况,指出CvaR在中国金融市场中应用应注意的问题,对其应用前景提出了新的思路。     

CVaR-EVT和BMM在极端金融风险管理中的应用研究

随着风险度量一致性原则的提出,研究发现金融机构广泛采用的VaR模型存在严重不足,尤其针对分布具有厚尾特征的极端金融风险无法有效度量。本文采用极值理论（EVT）解决VaR方法的尾部度量不足问题,利用CVaR-EVT和BMM模型分析美国、香港股票市场和我国沪深两市指数18年的日收益数据,研究发现：（1）在95％置信区间及点估计中,分位数为99%的CVaR-EVT所揭示的极端风险优于VaR的估计值;且BMM方法为实施长期极端风险管理提供了有力决策依据,其回报率受分段时区的影响,期间越长,风险估计值越高;（2）模型采用ML和BS方法统计估值显示,我国股票市场极端风险尾部估计值高于香港和美国市场;但是,国内市场逐步稳定,并呈现出跟进国际市场且差距缩小的发展趋势。     

Comparing VaR Approximation Methods that Use the First Four Moments as Inputs

This article compares four methods used to approximate value at risk (VaR) from the first four moments of a probability distribution: Cornish–Fisher, Edgeworth, Gram–Charlier, and Johnson distributions. Increasing rearrangements are applied to the first three methods. Simulation results suggest that for large sample situations, Johnson distributions yield the most accurate VaR approximation. For small sample situations with small tail probabilities, Johnson distributions yield the worst approximation. A particularly relevant case would be in banking applications for calculating the size of operational risk to cover certain loss types. For this case, the rearranged Gram–Charlier method is recommended.