Robust Inference of Risks of Large Portfolios

TL;DR

This paper introduces a bootstrap-based robust method for accurately estimating risk bounds in large portfolios, effectively handling model misspecification and heavy-tailed data.

Contribution

It extends the H-CLUB method with a robust approach using rank and quantile estimators, improving risk assessment for complex financial data.

Findings

The method outperforms traditional H-CLUB in simulations.

It effectively handles heavy-tailed and misspecified models.

Numerical results validate theoretical advantages.

Abstract

We propose a bootstrap-based robust high-confidence level upper bound (Robust H-CLUB) for assessing the risks of large portfolios. The proposed approach exploits rank-based and quantile-based estimators, and can be viewed as a robust extension of the H-CLUB method (Fan et al., 2015). Such an extension allows us to handle possibly misspecified models and heavy-tailed data. Under mixing conditions, we analyze the proposed approach and demonstrate its advantage over the H-CLUB. We further provide thorough numerical results to back up the developed theory. We also apply the proposed method to analyze a stock market dataset.