Estimation of the joint distribution of random effects for a discretely observed diffusion with random effects

Maud Delattre 1 Valentine Genon-Catalot 2 Catherine Larédo 3
3 M.I.A., I.N.R.A.
LPMA - Laboratoire de Probabilités et Modèles Aléatoires, MIA - Unité de recherche Mathématiques et Informatique Appliquées
Abstract : Mixed effects models are popular tools for analyzing longitudinal data from several individuals simultaneously. Individuals are described by N independent stochastic processes (Xi(t), t ∈ [0, T ]), i = 1,. .. , N , defined by a stochastic differential equation with random effects. We assume that the drift term depends linearly on a random vector Φi and the diffusion coefficient depends on another linear random effect Ψi. For the random effects, we consider a joint parametric distribution leading to explicit approximate likelihood functions for discrete observations of the processes Xi on a fixed time interval. The asymptotic behaviour of the associated estimators is studied when both the number of individuals and the number of observations per individual tend to infinity. The estimation methods are investigated on simulated and real neuronal data.
Document type :
Preprints, Working Papers, ...
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01446063
Contributor : Valentine Genon-Catalot <>
Submitted on : Wednesday, January 25, 2017 - 3:38:44 PM
Last modification on : Thursday, April 11, 2019 - 4:02:09 PM
Document(s) archivé(s) le : Wednesday, April 26, 2017 - 3:52:34 PM

File

EDSM_driftanddiff_25_01_17_MD....
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01446063, version 1

Citation

Maud Delattre, Valentine Genon-Catalot, Catherine Larédo. Estimation of the joint distribution of random effects for a discretely observed diffusion with random effects. 2017. ⟨hal-01446063⟩

Share

Metrics

Record views

400

Files downloads

263