Régularisation dans les Modèles Linéaires Généralisés Mixtes avec effet aléatoire autorégressif

Abstract : We address regularised versions of the Expectation-Maximisation (EM) algorithm for Generalised Linear Mixed Models (GLMM) in the context of panel data (measured on several individuals at different time points). A random response y is modelled by a GLMM, using a set X of explanatory variables and two random effects. The first effect introduces the dependence within individuals on which data is repeatedly collected while the second embodies the serially correlated time-specific effect shared by all the individuals. Variables in X are assumed many and redundant, so that regression demands regularisation. In this context, we first propose a L2-penalised EM algorithm for low-dimensional data, and then a supervised component-based regularised EM algorithm for the high-dimensional case.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01818544
Contributor : Catherine Trottier <>
Submitted on : Wednesday, August 7, 2019 - 10:51:00 AM
Last modification on : Wednesday, August 14, 2019 - 4:57:59 PM

Files

JDS2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01818544, version 1

Citation

Jocelyn Chauvet, Catherine Trottier, Xavier Bry. Régularisation dans les Modèles Linéaires Généralisés Mixtes avec effet aléatoire autorégressif. JdS 2017, 49èmes Journées de Statistique de la SFdS, May 2017, Avignon, France. ⟨hal-01818544⟩

Share

Metrics

Record views

97

Files downloads

5