Value at risk for non normally distributed market variables and incorporating event risk

Abstract

The paper present a new method for computing the VaR for a set of fixed income securities based on extreme value theory that models the tail probabilities directly without making any assumption about the distribution of entire return process. If compares the estimates of VaR for a portfolio of fixed income securities across three methods: Variance-Covariance method. Historical Simulation method and Extreme Value method and finds that extreme value method solves the problem of fatter tails and provides the best VaR estimator in terms of correct failure ratio and the size of VaR.