Multivariate conditional tail expectations

다변량 조건부 꼬리 기대값

  • Hong, C.S. (Department of Statistics, Sungkyunkwan University) ;
  • Kim, T.W. (Department of Statistics, Sungkyunkwan University)
  • Received : 2016.07.05
  • Accepted : 2016.10.27
  • Published : 2016.12.31


Value at Risk (VaR) for market risk management is a favorite method used by financial companies; however, there are some problems that cannot be explained for the amount of loss when a specific investment fails. Conditional Tail Expectation (CTE) is an alternative risk measure defined as the conditional expectation exceeded VaR. Multivariate loss rates are transformed into a univariate distribution in real financial markets in order to obtain CTE for some portfolio as well as to estimate CTE. We propose multivariate CTEs using multivariate quantile vectors. A relationship among multivariate CTEs is also derived by extending univariate CTEs. Multivariate CTEs are obtained from bivariate and trivariate normal distributions; in addition, relationships among multivariate CTEs are also explored. We then discuss the extensibility to high dimension as well as illustrate some examples. Multivariate CTEs (using variance-covariance matrix and multivariate quantile vector) are found to have smaller values than CTEs transformed to univariate. Therefore, it can be concluded that the proposed multivariate CTEs provides smaller estimates that represent less risk than others and that a drastic investment using this CTE is also possible when a diversified investment strategy includes many companies in a portfolio.

시장위험 관리를 위한 Value at Risk(VaR)는 금융기관들이 선호하는 기법이지만, 투자가 실패한 경우에 손실금액에 대하여는 설명할 수 없다는 문제점이 있다. VaR의 한계를 보완하는 대안적인 위험측정도구인 Conditional Tail Expectation(CTE)는 VaR를 초과하는 조건부 기대값으로 정의된다. 포트폴리오에 대한 CTE를 추정하는 실제금융시장에서는. 일반적으로는 다변량 손실률을 일변량 분포로 변환하여 VaR을 추정하고 CTE를 구하지만, 본 연구에서는 다차원 분위벡터를 이용하여 다변량 CTE들을 제안한다. 그리고 일변량 CTE들의 관계를 확장하여 다변량 CTE들의 관계식을 유도하였다. 다양한 분산-공분산행렬을 갖는 이변량과 삼변량의 정규분포로부터 다변량 CTE들을 구하고 CTE들의 관계식을 구현하면서 고차원 분포로의 확장 가능성을 설명하였다. 이변량과 삼변량의 실증 예제를 통해 제안한 이론을 탐색하고, 기존의 CTE와 비교하였다. 다변량 변수들의 분산-공분산행렬과 다변량 분위벡터를 사용한 다변량 CTE가 일변량으로 변환하여 구한 CTE보다 작은 값을 갖는 것을 발견하였다. 그러므로 본 연구에서 제안한 다변량 CTE는 보다 적은 위험성을 나타내는 추정량이며, 포트폴리오를 구성하는 여러 기업을 동시에 고려하는 분산 투자 전략을 세우는 경우에 이런 다변량 CTE를 사용하는 적극적인 투자가 가능하다는 장점이 있다.



  1. Acerbi, C. and Tasche, D. (2002). Expected shortfall: a natural coherent alternative to VaR, Economic Notes, 31, 379-388.
  2. Andersson, F., Mausser, H., Rosen, D., and Uryasev, S. (2001). Credit risk optimization with condition value-at-risk, Mathematical Programming, 89, 273-291.
  3. Artzner, P., Delbaen, F., Eber, J. M., and Heath, D. (1999). Coherent measures of risk, Mathematical Finance, 9, 203-228.
  4. Berkowitz, J., Christoffersen, P., and Pelletier, D. (2011). Evaluating value-at-risk models with desk-level data, Management Science, 57, 2213-2227.
  5. Heo, S. J., Yeo, S. C., and Kang, T. H. (2012). Performance analysis of economic VaR estimation using risk neutral probability distributions, Korean Journal of Applied Statistics, 25, 757-773.
  6. Hong, C. S., Han, S. J., and Lee, G. P. (2016). Vector at risk and alternative value at risk, Korean Journal of Applied Statistics, 29, 689-697.
  7. Hong, C. S. and Kwon, T. W. (2010). Distribution tting for the rate of return and value at risk, Journal of the Korean Data & Information Science Society, 21, 219-229.
  8. Hong, C. S. and Lee, J. H. (2011a). VaR estimation of multivariate distribution using copula functions, Korean Journal of Applied Statistics, 24, 523-533.
  9. Hong, C. S. and Lee, W. Y. (2011b). VaR estimation with multiple copula functions, Korean Journal of Applied Statistics, 24, 809-820.
  10. Jorion, P. (2007). Value at Risk: The New Benchmark for Controlling Market Risk, McGraw-Hill, New York.
  11. Kang, M., Kim, J., Song, J., and Song, S. (2013). Value at risk with peaks over threshold: comparison study of parameter estimation, Korean Journal of Applied Statistics, 26, 483-494.
  12. Krokhmal, P., Palmquist, J., and Uryasev, S. (2002). Portfolio optimization with conditional value-at-risk objective and constraints, Journal of Risk, 4, 43-68.
  13. Li, D. X. (1999). Value at risk based on the volatility skewness and kurtosis, Working paper, RiskMetrics Group, New York.
  14. Longin, F. M. (2000). From value at risk to stress testing: the extreme value approach, Journal of Banking & Finance, 24, 1097-1130.
  15. Longin, F. M. (2001). Beyond the VaR, Journal of Derivatives, 8, 36-48.
  16. Neftci, S. N. (2000). Value at risk calculations extreme events, and tail estimation, Journal of Derivatives, 7, 23-37.
  17. Park, J. S. and Jung, M. S. (2002). Market risk management strategy for VaR, Postal Information Review, 50, 81-104.
  18. Rockafellar, R. T. and Uryasev, S. (2000). Optimization of conditional value-at-risk, Journal of Risk, 2, 21-41.
  19. Sarykalin, S., Serraino, G., and Uryasev, S. (2008). Value-at-risk vs. conditional value-at-risk in risk management and optimization, Tutorials in Operations Research, 270-294.
  20. Seo, S. H. and Kim, S. G. (2010). Estimation of VaR using extra losses, and back-testing: case study, Korean Journal of Applied Statistics, 23, 219-234.
  21. Topaloglou, N., Vladimirou, H. and Zenios, S. A. (2002). CVaR models with selective hedging for international asset allocation, Journal of Banking & Finance, 26, 1535-1561.
  22. Yeo, S. C. and Li, Z. (2015). Performance analysis of volatility models for estimating portfolio value at risk, Korean Journal of Applied Statistics, 28, 541-599.
  23. Zangari, P. (1996). An improved methodology for measuring VaR, RiskMetrics Monitor, 2nd quarter, 7-25.