您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

山东大学学报(理学版) ›› 2017, Vol. 52 ›› Issue (2): 85-90.doi: 10.6040/j.issn.1671-9352.0.2016.033

• • 上一篇    下一篇

风险价值VaR的区间估计

任鹏程,徐静,李新民*   

  1. 青岛大学数学与统计学院, 山东 青岛 266071
  • 收稿日期:2016-01-19 出版日期:2017-02-20 发布日期:2017-01-18
  • 通讯作者: 李新民(1969— ),男,博士,教授,研究方向为数理统计及其应用.E-mail:xmli@qdu.edu.cn E-mail:renpengcheng12@qq.com
  • 作者简介:任鹏程(1992— ),男,硕士研究生,研究方向为数理统计及其应用.E-mail:renpengcheng12@qq.com
  • 基金资助:
    国家自然科学基金资助项目(11501314);山东省自然科学基金资助项目(ZR2014AM019)

Interval estimation of VaR

REN Peng-cheng, XU Jing, LI Xin-min*   

  1. School of Mathematics and Statistics, Qingdao University, Qingdao 266071, Shandong, China
  • Received:2016-01-19 Online:2017-02-20 Published:2017-01-18

摘要: 风险价值(value at risk, VaR)是国际金融界广泛支持和认可的一种度量金融风险的工具。分别利用Bootstrap、MOVER(method of variance estimates recovery)和Fiducial方法给出正态总体下VaR的区间估计方法,并进行了模拟比较。 模拟结果发现基于Fiducial思想的广义区间估计在覆盖率和区间等尾性上具有更稳健的性质。最后对上证180重点指数的对数收益率VaR进行了分析。

关键词: MOVER, Bootstrap法, 区间估计, 风险价值, 广义推断

Abstract: Value at risk(VaR)is a tool used for measuring financial risk, which is widely supported and recognized by international finance. To study the interval estimation method in normal population, we used three methods such as Bootstrap、MOVER(method of variance estimates recovery)and Fiducial, and numerically compare the performance of them. The simulation results show that generalized interval estimation based on Ficucial is more robust in coverage and balanced tail error. In the end, the VaR of logarithmic yield of SSE 180 was analyzed.

Key words: VaR, Bootstrap method, MOVER, generalized inference, interval estimation

中图分类号: 

  • O212.1
[1] 曾翀, 万建平. 基于Bootstrap方法的VaR区间估计[J]. 经济数学, 2009, 26(1): 58-63. ZENG Chong, WAN Jianping. Interval estimate for VaR based on bootstrap method [J]. Mathematics in Economics, 2009, 26(1):58-63.
[2] 缪柏其, 叶五一.高等计量经济学基础[M]. 北京: 高等教育出版社, 2013:162. MIAO Baiqi, YE Wuyi. The elements of advances in econometrics[M]. Beijing: Higher Education Press, 2013:162.
[3] TSAY R S. An introduction to analysis of financial data with R[M]. New York: John Wiley & Sons, 2012.
[4] MORAUX F. How valuable is your VaR? Large sample confidence intervals for normal VaR[J]. Journal of Risk Management in Financial Institutions, 2011, 4(2):189-200.
[5] EFRON B. Better bootstrap confidence intervals[J]. Journal of the American Statistical Association, 1987, 82(397):171-185.
[6] ZOU Guangyong, DONNER A. Construction of confidence limits about effect measures: a general approach[J]. Statistics in Medicine, 2008, 27(10):1693-1702.
[7] ZOU Guangyong, TALEBAN J, HUO C Y. Confidence interval estimation for lognormal data with application to health economics[J]. Computational Statistics & Data Analysis, 2009, 53(11):3755-3764.
[8] TSUI K W, WEERAHANDI S. Generalized p-values in significance testing of hypotheses in the presence of nuisance parameters[J]. Journal of the American Statistical Association, 1989, 84(406):602-607.
[9] WEERAHANDI S. Generalized confidence intervals[J]. Journal of the American Statistical Association, 1993, 88(423):899-905.
[10] LI Xinmin, LI Guoying. Confidence intervals on sum of variance components with unbalanced designs[J]. Communications in Statistics-Theory and Methods, 2005, 34(4):833-845.
[11] XU Xingzhong, LI Guoying. Fiducial inference in the pivotal family of distributions[J]. Science in China Series A, 2006, 49(3):410-432.
[12] HANNIG J, IYER H, PATTERSON P. Fiducial generalized confidence intervals[J]. Journal of the American Statistical Association, 2006, 101(473):254-269.
[1] 梁红燕, 许民利, 简惠云. 基于消费者选择偏好的可替代品订货策略[J]. 山东大学学报(理学版), 2015, 50(07): 80-88.
[2] 张良勇1,2,徐兴忠2,董晓芳1. 基于中位数排序集抽样的区间估计[J]. J4, 2013, 48(12): 107-110.
[3] 马玉林,王希泉 . 基于实际波动率的VaR模型实证研究[J]. J4, 2007, 42(10): 84-89 .
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!