Reparameterization of extreme value framework for improved Bayesian workflow

Théo Moins (1) , Julyan Arbel (1) , Stéphane Girard (1) , Anne Dutfoy (2)

1 STATIFY - Modèles statistiques bayésiens et des valeurs extrêmes pour données structurées et de grande dimension
2 EDF R&D PERICLES - PERformance et prévention des Risques Industriels du parC par la simuLation et les EtudeS

Using Bayesian methods for extreme value analysis offers an alternative to frequentist ones, with several advantages such as easily dealing with parametric uncertainty or studying irregular models. However, computation can be challenging and the efficiency of algorithms can be altered by poor modelling choices, and among them the parameterization is crucial. We focus on the Poisson process characterization of univariate extremes and outline two key benefits of an orthogonal parameterization. First, Markov chain Monte Carlo convergence is improved when applied on orthogonal parameters. This analysis relies on convergence diagnostics computed on several simulations. Second, orthogonalization also helps deriving Jeffreys and penalized complexity priors, and establishing posterior propriety thereof. Our framework is applied to return level estimation of Garonne flow data (France).

Domaines: Méthodologie [stat.ME]

Théo Moins, Julyan Arbel, Stéphane Girard, Anne Dutfoy. Reparameterization of extreme value framework for improved Bayesian workflow. Computational Statistics and Data Analysis, 2023, 187, pp.1-21. ⟨10.1016/j.csda.2023.107807⟩. ⟨hal-03806159v4⟩