Generating Yield Curve Stress-Scenarios

Arthur Charpentier and Christophe Villa
Additional contact information
Christophe Villa: CREM - Centre de recherche en économie et management - UNICAEN - Université de Caen Normandie - NU - Normandie Université - UR - Université de Rennes - CNRS - Centre National de la Recherche Scientifique

Working Papers from HAL

Abstract: Several authors have proposed to combine movements in princi- pal components to generate scenarios of "large" historical changes in term structures, i.e. stress-scenarios. This approach, however, has at least two shortcommings. This paper answers at these two problems and proposes a general two-steps procedure. The rst step relies on tting the discount bond yields and the second step relies on estimating statistically independent variables. Using the distribution of independent components identi ed, we combine their movements to produce stress-scenarios by specifying separate "shocks" in each of the directions given by the three independent compo- nents. We apply our methodology to the U.S. term structure of interest rates over the last three decades.

Keywords: Term structure; Yield curve; IRR; Stress-Testing; Scenario analysis; Principal Component Analysis; Independant Component Analy- sis.; Independant Component Analy- sis (search for similar items in EconPapers)
Date: 2010-12-28
Note: View the original document on HAL open archive server: https://hal.science/hal-00550582
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://hal.science/hal-00550582/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-00550582

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().