TailCoR
40 Pages Posted: 31 May 2012 Last revised: 13 May 2015
There are 2 versions of this paper
TailCoR
Date Written: May 13, 2015
Abstract
Economic and financial crises are characterized by tail events. When they occur, tail correlations emerge, which have linear and non-linear origins. The former are due to the Pearson correlations, while the strength of the latter depends on the heavyness of the tails. We introduce TailCoR, a new metric for tail correlations that disentangles straightforwardly the linear and non-linear correlations. TailCoR is simple to compute, no optimizations are needed, and it performs well in small samples. When applied to a panel of eight major US banks, TailCoR increases during the financial crisis because of a surge in both the linear and non-linear correlations. The end of 2012 also shows an increase of TailCoR, which is solely driven by the non-linearity, reflecting the risks of tail events and their spillovers associated with the European sovereign debt crisis.
Keywords: Tail correlation, tail risk, quantile, ellipticity, crises
JEL Classification: C32, C51, G01
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
Estimation of Continuous-Time Processes via the Empirical Characteristic Function
By George J. Jiang and John Knight
-
Empirical Characteristic Function Estimation and its Applications
By Jun Yu
-
Empirical Characteristic Function in Time Series Estimation
By John Knight and Jun Yu
-
Efficient Estimation Using the Characteristic Function
By Marine Carrasco and Rachidi Kotchoni
-
By Marine Carrasco, Mikhail Chernov, ...
-
Estimation of Stable Distributions by Indirect Inference
By René Garcia, Eric Renault, ...
-
Cross Validated Snp Density Estimates
By Mark Coppejans and A. Ronald Gallant
-
The Method of Simulated Quantiles
By Yves Dominicy and David Veredas
-
Indirect Estimation of Elliptical Stable Distributions
By Marco J. Lombardi and David Veredas