Bqgpd_d

WARNING: this function will not be exported in a future version of the package.

internal

A set of procedures for estimating risks related to extreme events via risk measures such as Expectile, Value-at-Risk, etc. is provided. Estimation methods for univariate independent observations and temporal dependent observations are available. The methodology is extended to the case of independent multidimensional observations. The statistical inference is performed through parametric and non-parametric estimators. Inferential procedures such as confidence intervals, confidence regions and hypothesis testing are obtained by exploiting the asymptotic theory. Adapts the methodologies derived in Padoan and Stupfler (2022) <doi:10.3150/21-BEJ1375>, Davison et al. (2023) <doi:10.1080/07350015.2022.2078332>, Daouia et al. (2018) <doi:10.1111/rssb.12254>, Drees (2000) <doi:10.1214/aoap/1019487617>, Drees (2003) <doi:10.3150/bj/1066223272>, de Haan and Ferreira (2006) <doi:10.1007/0-387-34471-3>, de Haan et al. (2016) <doi:10.1007/s00780-015-0287-6>, Padoan and Rizzelli (2024) <doi:10.3150/23-BEJ1668>, Daouia et al. (2024) <doi:10.3150/23-BEJ1632>.

Simone Padoan

ExtremeRisks

Extreme Risk Measures

Gilles Stupfler

Carlotta Pacifici

Bqgpd_d function

<dl><dt>p</dt>
<dd>probability levels</dd>
<dt>post</dt>
<dd>matrix of posterior samples</dd>
<dt>lower</dt>
<dd>lower bound for the search for the quantile</dd>
<dt>upper</dt>
<dd>upper bound for the region over which to search for the quantile</dd></dl>

Arguments

Bayesian predictive quantile for discrete generalized Pareto distribution — Bqgpd_d

<dl>

<dt>p</dt>
<dd>probability levels</dd>


<dt>post</dt>
<dd>matrix of posterior samples</dd>


<dt>lower</dt>
<dd>lower bound for the search for the quantile</dd>


<dt>upper</dt>
<dd>upper bound for the region over which to search for the quantile</dd>

</dl>

Bqgpd_d: Bayesian predictive quantile for discrete generalized Pareto distribution

Description

Usage

Value

Arguments