主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2014, Vol. 22 ›› Issue (8): 1-9.

• 论文 •    下一篇

VaR与CVaR的敏感性凸性及其核估计

黄金波1, 李仲飞2, 周先波3   

  1. 1. 广东财经大学金融学院, 广东 广州 510320;
    2. 中山大学管理学院, 广东 广州 510275;
    3. 中山大学岭南学院, 广东 广州 510275
  • 收稿日期:2013-07-01 修回日期:2014-03-10 出版日期:2014-08-20 发布日期:2014-08-23
  • 作者简介:黄金波(1983- ),男(汉族),河南信阳人,广东财经大学金融学院,讲师,博士,研究方向:金融风险计算、风险管理.
  • 基金资助:

    国家自然科学基金重点项目(71231008);教育部人文社会科学研究基金青年项目(12YJCZH267);广东省高等学校高层次人才项目;中央高校基本科研业务费专项资金资助项目(13wkpy28);国家自然科学基金项目(71371199)

Sensitivity and Convexity of VaR (CVaR) and Their Kernel Estimator

HUANG Jin-bo1, LI Zhong-fei2, ZHOU Xian-bo3   

  1. 1. Finance Department, Guangdong University of Finance and Economics, Guangzhou 510320, China;
    2. SYSBS, Sun Yat-sen Universtiy, Guangzhou 510275, China;
    3. Lingnan College, Sun Yat-sen Universtiy, Guangzhou 510275, China
  • Received:2013-07-01 Revised:2014-03-10 Online:2014-08-20 Published:2014-08-23

摘要: 风险价值(VaR)和条件风险价值(CVaR)是目前两大主流风险度量工具,如何准确地对它们进行估计是风险管理实践中首要而核心的问题。近年来非参数核估计方法因模型设定灵活、方便处理变量相依结构等优点备受关注。在本文,我们在核估计的框架内讨论VaR和CVaR估计量的性质;给出投资组合VaR和CVaR对组合头寸的一阶导数向量和二阶导数矩阵的核估计公式,并用它们来讨论组合VaR和CVaR对组合头寸的敏感性和凸性。最后,我们利用中国外汇市场的实际数据做实证分析。

关键词: 风险价值, 条件风险价值, 核估计, 凸性

Abstract: Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR) are two mainly popular risk measurement tools presently. How these risk measure indicators can be estimated accurately is the primary and central problem in the risk management practice. Nonparametric kernel estimation method has received broad attention recently because it can process dependent structure problem very easy and its model is flexible. In this paper, the kernel estimator of VaR and CVaR is investigated and firstly some properties of kernel estimator of VaR and CVaR are discussed. Then the investment portfolio's VaR and CVaR are definited and the analytical expression is derived for the first and second derivatives of the VaR and CVaR, which are used to analyze the sensitivity and convexity of VaR and CVaR. Finally, the kernel estimation method is used to estimate the sensitivity and convexity of VaR and CVaR.

Key words: value-at-risk, conditional value-at-risk, kernel estimation, convexity

中图分类号: