A0710
Title: Double-pooling for dynamic tail estimation
Authors: Shiqi Ye - AMSS Center for Forecasting Science, Chinese Academy of Sciences (China) [presenting]
Abstract: The aim is to propose a novel semiparametric framework for modeling the dynamic tail behavior of panel time series. The methodology introduces a "double-pooling" mechanism that effectively exploits both cross-sectional dependence and cross-quantile structures. This approach significantly enhances the accuracy and efficiency of estimating time-varying value-at-risk (VaR) and expected shortfall (ES). The asymptotic theory for the estimators is established, and formal hypothesis tests are developed to rigorously evaluate the proposed tail dynamics. An empirical application to European economies demonstrates the practical utility of the method in providing robust insights into dynamic growth-at-risk and expected shortfall, offering valuable implications for financial stability and risk management.
