Nonparametric estimator of the tail dependence coefficient: balancing bias and variance

by   Matthieu Garcin, et al.

A theoretical expression is derived for the mean squared error of a nonparametric estimator of the tail dependence coefficient, depending on a threshold that defines which rank delimits the tails of a distribution. We propose a new method to optimally select this threshold. It combines the theoretical mean squared error of the estimator with a parametric estimation of the copula linking observations in the tails. Using simulations, we compare this semiparametric method with other approaches proposed in the literature, including the plateau-finding algorithm.


POT-flavored estimator of Pickands dependence function

This work proposes an estimator with both Peak-Over-Threshold and Block-...

Improved Estimator of the Conditional Tail Expectation in the case of heavy-tailed losses

In this paper, we investigate the extreme-value methodology, to propose ...

Nonparametric local linear estimation of the relative error regression function for censorship model

In this paper, we built a new nonparametric regression estimator with th...

Regularizing Double Machine Learning in Partially Linear Endogenous Models

We estimate the linear coefficient in a partially linear model with conf...

Uncertainty Principles in Risk-Aware Statistical Estimation

We present a new uncertainty principle for risk-aware statistical estima...

The bias of isotonic regression

We study the bias of the isotonic regression estimator. While there is e...

Risk-Aware MMSE Estimation

Despite the simplicity and intuitive interpretation of Minimum Mean Squa...

Please sign up or login with your details

Forgot password? Click here to reset