《基于条件风险价值的股市风险分析》由会员分享，可在线阅读，更多相关《基于条件风险价值的股市风险分析（53页珍藏版）》请在金锄头文库上搜索。
1、论文题目：基于条件风险价值的股市风险分析作者姓名：陈 力 杰入学时间：2005 年 9 月专业名称：概率论与数理统计 研究方向：统计推断理论及应用指导教师：李 述 山职称：教授论文提交日期：2008 年 5 月论文答辩日期：2008 年 6 月授予学位日期：Stock Risk Analysis Based On Conditional Value-at-RiskA Dissertation submitted in fulfillment of the requirements of the degree ofMASTER OF SCIENCEfromShandong University
2、of Science and TechnologybyChen Li JieSupervisor: Professor Li ShushanCollege of information science and EngineeringMay 2008声明本人呈交给山东科技大学的这篇硕士学位论文，除了所列参考文献和世所公认的文献外，全部是本人在导师指导下的研究成果。该论文资料尚没有呈交于其它任何学术机关作鉴定。硕士生签名：日期：AFFIRMATIONI declare that this dissertation, submitted in fulfillment of the requireme
3、nts for theaward of Masters of Science in Shandong University of Science and Technology, is whollymy own work unless referenced of acknowledge. The document has not been submittedfor qualification at any other academic institute.Signature:Date:山东科技大学硕士学位论文摘要摘要风险是指未来结果的不确定性或波动性，如未来收益、资产或债务价值的波动性或不确定性
4、。金融市场风险测量就是测量由于市场因子的不利变化而导致金融资产(证券组合)价值损失的大小。目前，金融市场风险测量的主要方法包括均值方差分析、灵敏度分析 、波动性分析、VaR 和 CVaR 方法。CVaR(条件风险价值)方法是在 VaR(风险价值)方法的基础之上产生的，最早是由Rockafellar 在 1999 年底提出的，其含义损失超过 VaR 的条件均值，反映超额损失的平均水平。它较之于 VaR 风险测量方法，更能体现风险测量的潜在风险。CVaR 风险测量方法有多方面的应用，如信用风险的测量、内部风险资本金的确定、资本配置、金融监管等，本文主要研究的是 CVaR 在证券市场风险测量中的应用
5、，在研究的过程中，采用了系统理论、归纳演绎、比较与实证分析等研究方法。文章首先从总体上介绍了传统风险测量方法的发展过程及其在现实中的主要应用，然后再对 CVaR 风险测量方法进行深入的研究，对其概念、参数选择、计算、性质等方面都作了较详细的探讨，得出的结论是 CVaR 风险测量方法比传统的风险测量方法拥有更多的优点。再次，对 CVaR 在风险测量中的运用进行了深入的研究。由于金融资产收益序列不服从正态分布、尖峰厚尾、杠杆效应的特点，这里用APARCH 模型计算收益率序列的波动性，介绍了 APARCH 模型的特点，然后分别计算了基于正态分布、t 分 布 、GED 分布下的 VaR 和 CVaR，
6、并且比较了不同分布下的 VaR 和 CVaR在风险测量上的优越性。再就是以 CVaR 作为约束条件，计算投资组合最优化问题，并分别对这两个应用进行了实证研究，实质上，这两个应用的意义都是利用 CVaR 来指导投资决策，最终的目的是一样，不同的只是方法。再次，简单地阐述了 CVaR 在我国应用所面临的问题，并提出一些建议。关键词:VaR，CVaR，APARCH 模型，GED 分布，Kupiec 检验，DLC 统计量，投资组合山东科技大学硕士学位论文摘要AbstractRisk is defined as volatility of future, for example, future retu
7、rn and liabilities, value ofassets. Measurement of financial market risk is measuring loss resulting from unfavorable change.The methods of risk measurement include mean-volatility method, sensitivity analysis, volatilityanalysis and VaR and CVaR.The risk measure method of Conditional Value-at-Risk
8、is developed on basis of theshortcoming of Value-at-Risk method, which is raised by Rockafellar at 1999. The implication ofCVaR is the conditional loss over VaR of portfolio, which reflects the average exceed quota.CVaR method reflects underlying loss better than VaR method.CVaR has many application
9、s, such as measuring credit risk, deciding inner risk capital, assetallocation, banking supervision. This paper focuses on the applications of CVaR in the portfoliotheory. In the course of researching, I do my best to use the methods of systems theory, inductionand deduction, comparison and empirica
10、l analysis. Firstly, the paper totally introduces all kinds oftraditional risk measure methods and then analyses the defects of these methods, then putsforward CVaR risk measure method, introduces and analyses the definition, the parameterselecting, the calculation, the properties and applications a
11、nd so on. The conclusion is that CVaRis better than the traditional methods and CVaR method is a coherent risk measure method.For the return sequence do not obey normal distribution, peak and thick tail, balance effect,then using APPARCH model calculate the volatility of return sequence. and introdu
12、ce thecharacters of APPARCH, and then calculate the VaR and CVaR based on t distribution, GEDdistribution, normal distribution. Then compare the dominance of VaR and CVaR under differentdistributions. Secondly,the paper studies the application of CVaR in portfolio theory, the otheris the optimal sel
13、ection of portfolio on based of CVaR constraint. And using empirical analysisproved these two problems. In fact the implications of these two problems are identical. They alluse CVaR to guide invest decisions. Thirdly, the paper simply analyses the problems of the use ofCVaR in China and puts forwards some suggestions.Keywords: VaR, CVaR, GED distribution, Kupiec test, DLC statistic, APARCH Model,Portfolio山东科技大学硕士学位论文目录目录第 1 章 绪论.11.1 金融风险定义及类型.
