Dynamic tail risk forecasting: what do realized skewness and kurtosis add?

TL;DR

This study evaluates how incorporating realized skewness and kurtosis improves tail risk forecasts like VaR and ES for US stocks, highlighting their significance for more accurate risk measurement.

Contribution

It introduces new model specifications that include realized skewness and kurtosis, demonstrating their impact on improving tail risk forecast accuracy.

Findings

Realized skewness and kurtosis enhance tail risk forecast precision.

Model performance varies with window length and model type.

Inclusion of higher moments improves risk management practices.

Abstract

This paper compares the accuracy of tail risk forecasts with a focus on including realized skewness and kurtosis in "additive" and "multiplicative" models. Utilizing a panel of 960 US stocks, we conduct diagnostic tests, employ scoring functions, and implement rolling window forecasting to evaluate the performance of Value at Risk (VaR) and Expected Shortfall (ES) forecasts. Additionally, we examine the impact of the window length on forecast accuracy. We propose model specifications that incorporate realized skewness and kurtosis for enhanced precision. Our findings provide insights into the importance of considering skewness and kurtosis in tail risk modeling, contributing to the existing literature and offering practical implications for risk practitioners and researchers.