Filtering the Wright-Fisher diffusion

Abstract : We consider a Wright-Fisher diffusion whose current state cannot be observed directly. Instead, at times < < ..., the observations are such that, given the process , the random variables are independent and the conditional distribution of only depends on . When this conditional distribution has a specific form, we prove that the model , 1) is a computable filter in the sense that all distributions involved in filtering, prediction and smoothing are exactly computable. These distributions are expressed as finite mixtures of parametric distributions. Thus, the number of statistics to compute at each iteration is finite, but this number may vary along iterations.
Keywords : Mathematics
Type de document :
Article dans une revue
ESAIM: Probability and Statistics, EDP Sciences, 2009, 13, pp.197-217. <10.1051/ps:2008006>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00491252
Contributeur : Hal Peer <>
Soumis le : vendredi 11 juin 2010 - 02:51:14
Dernière modification le : mardi 11 octobre 2016 - 11:59:11
Document(s) archivé(s) le : jeudi 1 décembre 2016 - 06:28:57

Fichier

PEER_stage2_10.1051%2Fps%3A200...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Mireille Chaleyat-Maurel, Valentine Genon-Catalot. Filtering the Wright-Fisher diffusion. ESAIM: Probability and Statistics, EDP Sciences, 2009, 13, pp.197-217. <10.1051/ps:2008006>. <hal-00491252>

Partager

Métriques

Consultations de
la notice

57

Téléchargements du document

20