Measurement of Common Risk Factors: A Panel Quantile Regression Model for Returns

TL;DR

This paper introduces a novel Panel Quantile Regression Model for Returns to measure market risk factors, demonstrating superior performance in Value-at-Risk forecasting and systemic risk identification.

Contribution

The paper proposes a new Panel Quantile Regression approach with penalized fixed effects, improving risk factor measurement and portfolio risk forecasting over benchmark models.

Findings

Outperforms benchmarks in 5 ext% and 10 ext% quantiles

Enhances Value-at-Risk forecasting accuracy

Provides better systemic risk identification

Abstract

This paper investigates how to measure common market risk factors using newly proposed Panel Quantile Regression Model for Returns. By exploring the fact that volatility crosses all quantiles of the return distribution and using penalized fixed effects estimator we are able to control for otherwise unobserved heterogeneity among financial assets. Direct benefits of the proposed approach are revealed in the portfolio Value-at-Risk forecasting application, where our modeling strategy performs significantly better than several benchmark models according to both statistical and economic comparison. In particular Panel Quantile Regression Model for Returns consistently outperforms all the competitors in the 5\% and 10\% quantiles. Sound statistical performance translates directly into economic gains which is demonstrated in the Global Minimum Value-at-Risk Portfolio and Markowitz-like comparison. Overall results of our research are important for correct identification of the sources of systemic risk, and are particularly attractive for high dimensional applications.