Kernel estimation of extreme regression risk measures (Q1697481)

Let \( Y \) be a positive random variable and \( X \in \mathbb{R}^{p} \) a random vector of regressors recorded simultaneously with \( Y \). Define the conditional survival function \( \bar{F}( \cdot \mid x ) = \mathbb{P}( Y> \cdot \mid X=x)\) and the conditional quantile \( \bar{F}^{\leftarrow}( \alpha \mid x ) =\inf \{t, \bar{F}( t \mid x) \leq \alpha\}\), \( \alpha \in(0,1)\). The regression conditional tail moment (RCTM) of level \( \alpha \in (0,1)\) and order \( b \geq 0 \) is the risk measure defined by \[ \mathrm{RCTM}_{b}( \alpha\mid x) :=\mathbb{E}\left( Y^{b}\mid Y > \bar{F}^{\leftarrow}(\alpha \mid x), \; X=x\right). \] From the authors' summary: ``The purpose of this work is first to establish the asymptotic properties of the RCTM in case of extreme losses, i.e., when \( \alpha \rightarrow 0 \) is no longer fixed, under general extreme-value conditions on their distribution tail. In particular, no assumption is made on the sign of the associated extreme-value index. Second, the asymptotic normality of a kernel estimator of the RCTM is established, which allows to derive similar results for estimators of related risk measures such as the Regression Conditional Tail Expectation/Variance/Skewness. When the distribution tail is upper bounded, an application to frontier estimation is also proposed. The results are illustrated both on simulated data and on a real dataset in the field of nuclear reactors reliability.''