Filtering the Wright-Fisher diffusion

Abstract : We consider a Wright-Fisher diffusion (x(t)) whose current state cannot be observed directly. Instead, at times t1 < t2 < . . ., the observations y(ti ) are such that, given the process (x(t)), the random variables (y(ti )) are independent and the conditional distribution of y(ti ) only depends on x(ti ). When this conditional distribution has a specific form, we prove that the model ((x(ti ), y(ti )), i 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.
Type de document :
Pré-publication, Document de travail
24 pages. 2007
Liste complète des métadonnées

Littérature citée [5 références]  Voir  Masquer  Télécharger
Contributeur : Valentine Genon-Catalot <>
Soumis le : mardi 3 juillet 2007 - 20:53:01
Dernière modification le : mercredi 21 mars 2018 - 18:56:48
Document(s) archivé(s) le : jeudi 8 avril 2010 - 22:29:49


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00159728, version 1
  • ARXIV : 0707.0537



Mireille Chaleyat-Maurel, Valentine Genon-Catalot. Filtering the Wright-Fisher diffusion. 24 pages. 2007. 〈hal-00159728〉



Consultations de la notice


Téléchargements de fichiers