Title page for etd-0728114-212246


[Back to Results | New Search]

URN etd-0728114-212246
Author Ching-yi Lin
Author's Email Address No Public.
Statistics This thesis had been viewed 5332 times. Download 0 times.
Department Applied Mathematics
Year 2013
Semester 2
Degree Master
Type of Document
Language English
Title Importance sampling estimation of portfolio expected shortfall via copula approach
Date of Defense 2014-07-24
Page Count 31
Keyword
  • D-vine
  • copula
  • kernel density estimation
  • expected shortfall
  • importance sampling
  • C-vine
  • Abstract Expected shortfall is a measure of financial portfolio risk. In this study, we consider the problem of estimating expected shortfall of a portfolio. We use bivariate copula to describe the dependence between two variables. And construct joint density for the assets of the portfolio using C-vine or D-vine approach based on pair-copulas. We draw bootstrap samples from the fitted copula-based joint distribution and estimate the density of the portfolio loss by kernel method. Regression method is further used to smooth the kernel estimator for the tail part of the density function. To improve estimation efficiency of the expected shortfall, we use the importance sampling estimate based on exponential truncation approach.
    Advisory Committee
  • Mong-Na Lo Huang - chair
  • May-Ru Chen - co-chair
  • Chung Chang - co-chair
  • Shih-Feng Huang - co-chair
  • Mei-Hui Guo - advisor
  • Files
  • etd-0728114-212246.pdf
  • Indicate in-campus at 5 year and off-campus access at 5 year.
    Date of Submission 2014-08-28

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys