Simulation, Bayes, and bootstrap in statistical hydrology.

Fortin, Vincent; Bernier, Jacques ORCID: https://orcid.org/0000-0002-0594-5922 et Bobée, Bernard (1997). Simulation, Bayes, and bootstrap in statistical hydrology. Water Resources Research , vol. 33 , nº 3. pp. 439-448. DOI: 10.1029/96WR03355.

Prévisualisation

PDF Télécharger (910kB) | Prévisualisation

Résumé

Statistical simulation in hydrology is discussed from a Bayesian perspective. The inherent difficulties in both parametric simulation, based on a parent distribution, and classical nonparametric simulation, based on the bootstrap, are discussed. As an alternative to these procedures, a nonparametric Bayesian simulation methodology, Pólya resampling, is introduced. It consists of simulating from a nonparametric predictive distribution obtained from the analysis of a reference sample, and it is asymptotically equivalent to the bootstrap. The method is generalized to take into account a prior hypothesis on the parametric distribution of a variable. A hybrid simulation model is then obtained that includes parametric and nonparametric simulation as particular cases. An extensive application is presented in a related paper [Fortin et al., 1997], where Pólya resampling is used to compare statistical models for flood frequency analysis. In this paper an example is used to demonstrate how Pólya resampling can help assess the influence of a distribution hypothesis on simulation results.

Type de document:	Article
Mots-clés libres:	bayesian statistics; bootstrap method; hydrological model; statistical hydrology
Centre:	Centre Eau Terre Environnement
Date de dépôt:	29 nov. 2019 15:16
Dernière modification:	16 févr. 2022 21:07
URI:	https://espace.inrs.ca/id/eprint/9453

Gestion Actions (Identification requise)

Modifier la notice