当前位置:主页 > 管理论文 > 信贷论文 >

基于Copula函数-Asymmetric Laplace分布的金融市场风险度量与套期保值研究

发布时间:2018-01-13 22:22

  本文关键词:基于Copula函数-Asymmetric Laplace分布的金融市场风险度量与套期保值研究 出处:《华中科技大学》2013年博士论文 论文类型:学位论文


  更多相关文章: 金融市场风险 金融市场风险度量 套期保值 Copula函数 VaR


【摘要】:随着金融全球一体化的发展,金融市场的复杂程度日益提高,防范金融风险已成为全社会的共识。加强金融系统风险防范和管理能力,提高市场转移及消化吸收风险的能力,将是我国金融市场健康成长和发展的重要保障。金融秩序和金融运行环境的不断改变,金融风险的产生、传播、控制与管理等都日趋复杂,对金融市场风险的度量与管理的研究也更加重要和复杂。金融市场风险是最常见也是我国金融机构面临的主要风险,但是对其的研究,一些传统的基于正态、线性或波动性对称等模型的研究已不再适用,很难充分地捕获市场风险信息。这就需要不断探索研究,给出更多适应现阶段风险管理要求的理论模型研究及实证研究。 本文在分析现代金融风险管理理论的基础上,总结了市场风险度量及期货套期保值等方面的研究,指出了现有研究的不足,针对金融市场风险的复杂性,建立了基于非正态分布方法及非线性相关性模型的风险度量模型和套期保值策略模型,对金融市场风险的度量与套期保值进行了研究。主要从以下四个方面展开了主体部分的研究: (1)本文建立了基于Asymmetric Laplace(AL)分布的市场风险VaR与CVaR的度量模型。构建了市场风险VaR和CVaR度量的AL参数法和AL-MC法,并进行了比较研究。选取上证指数、日经225指数及SP500指数为研究对象,结合各股市的风险特征,给出了VaR和CVaR度量及其返回检验和准确性评价。结果表明,基于AL分布的风险度量模型能更好刻画市场风险特征,能很好地度量市场风险。 (2)本文建立了动态风险VaR和CVaR度量的ARMA-GJR-AL模型。从相关性、波动性及残差分布特征三方面考虑,研究了基于ARMA-GJR-AL模型的动态风险VaR和CVaR的度量。通过实证研究,给出了上海股市与纽约股市的市场风险预测及准确性检验,,研究了模型的有效性。结果表明,基于AL分布的动态风险度量模型更具合理性和适用性,能有效地度量风险。 (3)本文运用Copula函数技术来描述资产间的相关性结构,建立了金融资产组合的市场风险VaR和CVaR的度量和分配的Copula-AL模型,并对常用的基于多元统计分布的度量方法及基于OLS模型的风险分配方法进行了比较研究。选取上证指数和深圳成指的组合为例,计算了组合风险及其分配。结果表明,基于t-Copula-AL模型的VaR、CVaR法计算简单准确,且能方便地进行风险分配。 (4)本文采用参数和非参数分布法来刻画边际分布特征,结合Copula函数技术来描述期现市场间的相关性,以CVaR最小化为目标函数,建立了基于静态和动态Copula-CVaR的最优套保比率度量模型,并对各模型进行了比较研究。以沪深300指数现货和期货为研究对象,建立了静态和动态Copula-CVaR模型及OLS模型,在给定套保期限内,分析了各模型的套保费用,并给出了修正成本套保效率的比较分析。实证结果表明,考虑套保费用时,应选择简单易行的静态套保策略,即使市场条件相同,也应据自身的费用情况选择最优套保策略。 本文的研究促进了金融市场风险度量、期货套期保值、AL分布及Copula函数理论等方面的研究,具有很好的理论意义,同时对投资决策、经济资本管理及风险管理等实践活动也起到很好的帮助和借鉴作用。
[Abstract]:With the development of global financial integration, the complexity of the financial market is increasing, the prevention of financial risks has become the consensus of the whole society. To strengthen the financial system risk prevention and management ability, improve the ability of digestion and absorption and transfer market risk, will be our country financial market an important guarantee for the healthy growth and development of the constantly changing financial order and. The financial environment, financial risk, communication, control and management are becoming more and more complex, the research on financial market risk measurement and management is more important and complex. Financial market risk is the most common major risks facing China's financial institutions, but the research, based on the traditional normal the study of linear or volatility symmetry model is no longer applicable, it is difficult to fully capture the market risk information. This requires continuous exploration and research, give more suitable at this stage of the wind The theoretical model research and Empirical Study of risk management requirements.
Based on the analysis of modern financial risk management theory, summarizes the research of market risk measurement and Futures Hedging etc., points out the shortcomings of existing studies, aiming at the complexity of financial market risk, establish the risk of non normal distribution method and nonlinear correlation model measurement model and hedging strategy based on the model of the measure of financial market risk and hedging are studied. Mainly from the following four aspects of the research of the main part:
(1) is established in this paper based on Asymmetric Laplace (AL) model to measure market risk VaR and CVaR distribution. The construction parameters of the AL method and AL-MC method of VaR and CVaR to measure market risk, and a comparative study. Select the Shanghai index, Nikkei 225 index and SP500 index as the research object, combined with the characteristics of the risk the stock market, given the VaR and CVaR measure and return test and evaluation. The results show that the risk distribution of AL metric model can better describe the market risk based on the features, can be a good measure of market risk.
(2) this paper establishes the ARMA-GJR-AL model of dynamic risk VaR and CVaR metrics. From the correlation, volatility and residual distribution characteristics of three aspects, the research of dynamic risk measures of VaR and CVaR based on the ARMA-GJR-AL model. Through empirical research, market risk prediction accuracy and gives the Shanghai stock market and New York stock market test, research the validity of the model. The results show that the dynamic risk measurement model of AL distribution is more reasonable and based on the application, can effectively measure the risk.
(3) this paper uses the Copula function to describe the correlation between assets structure and technology, established the Copula-AL model to measure the market risk of CVaR and VaR combination of financial assets and distribution, and the measurement methods of multivariate statistical distribution and risk allocation method based on OLS model are studied based on the commonly used combination of Shanghai Composite Index and. Shenzhen stock market as an example, the calculation of portfolio risk and distribution. The results show that the t-Copula-AL model based on VaR, the CVaR method is simple and accurate, and can carry out risk distribution conveniently.
(4) this paper uses parametric and non parametric distribution method to describe the marginal distribution characteristics, combined with the Copula function to describe the correlation between the current market, with the goal of minimizing CVaR function, established the optimal hedging ratio of static and dynamic measurement model based on the Copula-CVaR rate, and the model is studied. The Shanghai and Shenzhen 300 and the stock index futures as the research object, established the static and dynamic Copula-CVaR model and OLS model in a given period, set limits, analysis of the cost of insurance set of each model, and gives the correct cost of hedging efficiency is analyzed. The empirical results show that considering the hedging costs, should choose the static hedging strategy is simple and, even if the market conditions are the same, should also choose the optimal hedging strategy according to their own expenses.
This paper promotes the financial market risk measurement, futures hedging, the research of AL distribution and Copula function theory, is of great theoretical significance, at the same time on investment decisions, economic capital management and risk management practices also play a very good help and reference.

【学位授予单位】:华中科技大学
【学位级别】:博士
【学位授予年份】:2013
【分类号】:F224;F831.51

【参考文献】

相关期刊论文 前10条

1 胡援成,姜光明;上证综指收益波动性及VaR度量研究[J];当代财经;2004年06期

2 曾健,陈俊芳;Copula函数在风险管理中的应用研究——以上证A股与B股的相关结构分析为例[J];当代财经;2005年02期

3 黄诒蓉;罗奕;;资本市场分形结构的理论与方法[J];当代财经;2006年03期

4 高全胜;金融风险计量理论前沿与应用[J];国际金融研究;2004年09期

5 田新时,刘汉中,李耀;沪深股市一般误差分布(GED)下的VaR计算[J];管理工程学报;2003年01期

6 刘小茂,田立;VaR与CVaR的对比研究及实证分析[J];华中科技大学学报(自然科学版);2005年10期

7 陈守东,俞世典;基于GARCH模型的VaR方法对中国股市的分析[J];吉林大学社会科学学报;2002年04期

8 陈守东;胡铮洋;孔繁利;;Copula函数度量风险价值的Monte Carlo模拟[J];吉林大学社会科学学报;2006年02期

9 付胜华;檀向球;;股指期货套期保值研究及其实证分析[J];金融研究;2009年04期

10 单国莉,陈东峰;一种确定最优Copula的方法及应用[J];山东大学学报(理学版);2005年04期

相关博士学位论文 前1条

1 李梦玄;金融市场相依性Copula模型及实证研究[D];华中科技大学;2009年



本文编号:1420812

资料下载
论文发表

本文链接:https://www.wllwen.com/guanlilunwen/bankxd/1420812.html


Copyright(c)文论论文网All Rights Reserved | 网站地图 |

版权申明:资料由用户ed19e***提供,本站仅收录摘要或目录,作者需要删除请E-mail邮箱bigeng88@qq.com