Component-based regularisation of multivariate generalised linear mixed models
| Autor: | Catherine Trottier, Jocelyn Chauvet, Xavier Bry |
|---|---|
| Přispěvatelé: | Institut Montpelliérain Alexander Grothendieck (IMAG), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Université Paul-Valéry - Montpellier 3 (UPVM) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Statistics and Probability
Mixed model Multivariate statistics structural relevance supervised components Mathematics - Statistics Theory Statistics Theory (math.ST) 01 natural sciences Generalized linear mixed model 010104 statistics & probability [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] Lasso (statistics) Statistics Linear regression FOS: Mathematics Discrete Mathematics and Combinatorics random effects 0101 mathematics Mathematics [STAT.AP]Statistics [stat]/Applications [stat.AP] generalised linear regression 010401 analytical chemistry 16. Peace & justice Random effects model Regression 0104 chemical sciences Grouped data [STAT]Statistics [stat] Statistics Probability and Uncertainty [STAT.ME]Statistics [stat]/Methodology [stat.ME] |
| Zdroj: | Journal of Computational and Graphical Statistics Journal of Computational and Graphical Statistics, Taylor & Francis, In press, ⟨10.1080/10618600.2019.1598870⟩ |
| ISSN: | 1061-8600 1537-2715 |
| Popis: | We address the component-based regularisation of a multivariate Generalised Linear Mixed Model (GLMM) in the framework of grouped data. A set Y of random responses is modelled with a multivariate GLMM, based on a set X of explanatory variables, a set A of additional explanatory variables, and random effects to introduce the within-group dependence of observations. Variables in X are assumed many and redundant so that regression demands regularisation. This is not the case for A, which contains few and selected variables. Regularisation is performed building an appropriate number of orthogonal components that both contribute to model Y and capture relevant structural information in X. To estimate the model, we propose to maximise a criterion specific to the Supervised Component-based Generalised Linear Regression (SCGLR) within an adaptation of Schall's algorithm. This extension of SCGLR is tested on both simulated and real grouped data, and compared to ridge and LASSO regularisations. Supplementary material for this article is available online. Journal of Computational and Graphical Statistics, Taylor & Francis, In press |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|