Risk Analysis Using Regression Quantiles: Evidence from International Equity Markets

Abstract

In this paper we study risk management based on the quantile regression. Unlike the traditional VaR estimation methods, the quantile regression approach allows for a general treatment on the error distribution and is robust to distributions with heavy tails. We estimate the VaRs of five international equity indexes based on AR-ARCH model via quantile regressions. The empirical application show that the quantile regression based method is well suited to handle negative skewness and heavy tails in stock return time series.

Keywords: Value at risk, international equities, quantile regression, risk analysis

JEL Classification: G110, G150, C18