Xing Wang
Chinese Academy of Sciences
Room: M3 3127
Extreme and Inference for Tail Gini Functionals and Tail-Gini Co-variation
Tail risk analysis focuses on the problem of risk measurement on the tail regions of financial variables. As one important task in tail risk analysis for risk management, the measurement of tail risk variability is less addressed in the literature, and neither the theoretical nor practical methods are fully developed, which results into the difficulty of practical implementation. In this talk, we consider the measurement of tail variability under the tail scenarios of a systemic variable by extending the Gini's methodology. We propose the Tail Gini Functional and Tail Gini Co-variation.
As we are very interested in the limit of the proposed measures as the risk level approaches to the extreme status, we showed, by using extreme value techniques, how the tail dependence structure and marginal risk quantity have influences on the limit of the proposed tail variability measures.
Furthermore, we construct a nonparametric estimator and its asymptotic behavior is explored.