High level quantile approximations of sums of risks
Authors:
Open Access
- 16 April 2015
- journal article
- research article
- Published by Walter de Gruyter GmbH in Dependence Modeling
- Vol. 3 (1)
Abstract
The approximation of a high level quantile or of the expectation over a high quantile (Value at Risk (VaR) or Tail Value at Risk (TVaR) in risk management) is crucial for the insurance industry.We propose a new method to estimate high level quantiles of sums of risks. It is based on the estimation of the ratio between the VaR (or TVaR) of the sum and the VaR (or TVaR) of the maximum of the risks. We show that using the distribution of the maximum to approximate the VaR is much better than using the marginal. Our method seems to work well in high dimension (100 and higher) and gives good results when approximating the VaR or TVaR in high levels on strongly dependent risks where at least one of the risks is heavy tailed.Keywords
This publication has 11 references indexed in Scilit:
- Value-at-Risk Bounds with Variance ConstraintsSSRN Electronic Journal, 2013
- Risk Measures and Multivariate Extensions of Breiman's TheoremJournal of Applied Probability, 2012
- The AEP algorithm for the fast computation of the distribution of the sum of dependent random variablesBernoulli, 2011
- Asymptotic Results for the Sum of Dependent Non-identically Distributed Random VariablesMethodology and Computing in Applied Probability, 2008
- Diversification for general copula dependenceStatistica Neerlandica, 2007
- On the Tail Behavior of Sums of Dependent RisksASTIN Bulletin, 2006
- Analysis of the Expected Shortfall of Aggregate Dependent RisksASTIN Bulletin, 2005
- Asymptotic expansions of convolutions of regularly varying distributionsJournal of the Australian Mathematical Society, 2005
- Bivariate Survival Models Induced by FrailtiesJournal of the American Statistical Association, 1989
- Compound gamma, beta and F distributionsMetrika, 1970