Dspace de universite Djillali Liabes de SBA >
Thèse de Doctorat en Sciences >
Mathématiques >
Veuillez utiliser cette adresse pour citer ce document :
http://hdl.handle.net/123456789/2342
|
Titre: | Convergence presque complète des suites de variables aléatoires dépendantes, Applications aux modèles autorégressifs non linéaires. |
Auteur(s): | BOULENOIR, Zouaouia Encadreur: BENAISSA, SAMIR |
Mots-clés: | Autoregressive process complete convergence estimation tail probabilities linearly negative quadrant dependent sequence random variables weighted sums nonlinear autoregressive models extended negatively dependent sequence exponential inequality autoregressive Hilbertian process widely orthant dependent random variables |
Date de publication: | 17-sep-2018 |
Résumé: | The dissertation is composed of four chapters. In the first chapter, we explain the basic notions and highlight some of the objectives of time series analysis. In chapter two, we study a new concentration inequality and complete convergence of weighted sums for arrays of row-wise linearly negative quadrant dependent random variables, then in chapter three we demonstrate almost complete convergence of dependant random variables sequences with application to non-linear autoregressive processes model. Regarding the fourth and last chapter, we discuss the almost complete convergence of the value of the process of autoregressive Hilbertian of order one. |
Description: | Doctorat en sciences |
URI/URL: | http://hdl.handle.net/123456789/2342 |
Collection(s) : | Mathématiques
|
Fichier(s) constituant ce document :
|
Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.
|