M
Marie-Anne Poursat
Researcher at Université Paris-Saclay
Publications - 5
Citations - 120
Marie-Anne Poursat is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: Bayesian information criterion & Random effects model. The author has an hindex of 4, co-authored 5 publications receiving 92 citations. Previous affiliations of Marie-Anne Poursat include Département de Mathématiques.
Papers
More filters
Journal ArticleDOI
A note on BIC in mixed-effects models
TL;DR: In this paper, an appropriate BIC expression that is consistent with the random effect structure of the mixed effects model is derived, which is used for variable selection in mixed effects models.
Journal ArticleDOI
Influence Function for Robust Phylogenetic Reconstructions
TL;DR: The ability of influence function to produce new evolution hypotheses is shown, providing a new tool for filtering data sets (nucleotides, amino acids, and others) in the context of ML phylogenetic reconstructions.
Journal ArticleDOI
An iterative algorithm for joint covariate and random effect selection in mixed effects models.
Maud Delattre,Marie-Anne Poursat +1 more
TL;DR: A stepwise selection algorithm to perform simultaneous selection of the fixed and random effects in general mixed-effects models is proposed based on Bayesian Information criteria whose penalties are adapted to mixed- effects models.
BIC selection procedures in mixed effects models
TL;DR: In this article, a Bayesian Information Criterion (BIC) was proposed for variable selection in nonlinear mixed-e ects hidden Markov models, where the consistency rates of the maximum likelihood estimators (MLE) of the parameters depend on the level of variability designed in the model.
Posted Content
An iterative algorithm for joint covariate and random effect selection in mixed effects models
Maud Delattre,Marie-Anne Poursat +1 more
TL;DR: In this article, a stepwise selection algorithm is proposed to perform simultaneous selection of the fixed and random effects in general mixed-effects models, which is based on BIC-type criteria whose penalties are adapted to mixed effects models.