Mixture of generalized linear models: identifiability and applications - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Mixture of generalized linear models: identifiability and applications

Mélange de modèles linéaires généralisés: identifiabilité et applications

Résumé

We consider finite mixtures of generalized linear models with binary output. We prove that cross moments till order 3 are sufficient to identify all parameters of the model. We propose a least squares estimation method and we prove the consistency and the Gaussian asymptotic behavior of the estimator. An R-package is developed to apply our method, we give numerical experiments to compare with likelihood methods. We then provide new identifiability results for several finite mixtures of generalized linear models with binary output and unknown link function including both continuous and categorical covariates, and possibly longitudinal data.
Fichier principal
Vignette du fichier
article.pdf (621.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01908709 , version 1 (31-10-2018)
hal-01908709 , version 2 (29-01-2020)

Identifiants

Citer

Benjamin Auder, Elisabeth Gassiat, Mor Absa Loum. Mixture of generalized linear models: identifiability and applications. 2018. ⟨hal-01908709v1⟩
77 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More