The purpose of this article is to estimate value at risk (VaR) using quantile regression and provide a risk analysis for defaultable bond portfolios.
The method proposed is based on quantile regression pioneered by Koenker and Bassett. The quantile regression approach allows for a general treatment on the error distribution and is robust to distributions with heavy tails.
This article provides a risk analysis for defaultable bond portfolios using quantile regression method. In the proposed model we use information variables such as short‐term interest rates and term spreads as covariates to improve the estimation accuracy. The study also finds that confidence intervals constructed around the estimated VaRs can be very wide under volatile market conditions, making the estimated VaRs less reliable when their accurate measurement is most needed.
Provides a risk analysis for defaultable bond using quantile regression approach.
