Measuring Portfolio Risk Under Partial Dependence Information

21 Pages Posted: 9 Aug 2018

See all articles by Carole Bernard

Carole Bernard

Grenoble Ecole de Management; Vrije Universiteit Brussel (VUB)

M. Denuit

Catholic University of Louvain (UCL)

Steven Vanduffel

Vrije Universiteit Brussel (VUB)

Multiple version iconThere are 2 versions of this paper

Date Written: September 2018

Abstract

The bounds for risk measures of a portfolio when its components have known marginal distributions but the dependence among the risks is unknown are often too wide to be useful in practice. Moreover, availability of additional dependence information, such as knowledge of some higher‐order moments, makes the problem significantly more difficult. We show that replacing knowledge of the marginal distributions with knowledge of the mean of the portfolio does not result in significant loss of information when estimating bounds on value‐at‐risk. These results are used to assess the margin by which total capital can be underestimated when using the Solvency II or RBC capital aggregation formulas.

Suggested Citation

Bernard, Carole and Denuit, M. and Vanduffel, Steven, Measuring Portfolio Risk Under Partial Dependence Information (September 2018). Journal of Risk and Insurance, Vol. 85, Issue 3, pp. 843-863, 2018, Available at SSRN: https://ssrn.com/abstract=3228188 or http://dx.doi.org/10.1111/jori.12165

Carole Bernard (Contact Author)

Grenoble Ecole de Management ( email )

12, rue Pierre Sémard
Grenoble Cedex, 38003
France

Vrije Universiteit Brussel (VUB) ( email )

Pleinlaan 2
http://www.vub.ac.be/
Brussels, 1050
Belgium

M. Denuit

Catholic University of Louvain (UCL) ( email )

Place Montesquieu, 3
Louvain-la-Neuve, 1348
Belgium

Steven Vanduffel

Vrije Universiteit Brussel (VUB) ( email )

Pleinlaan 2
Brussels, Brabant 1050
Belgium

HOME PAGE: http://www.stevenvanduffel.com

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
0
Abstract Views
419
PlumX Metrics