Addressing cluster-constant covariates in mixed effects models via likelihood-based boosting techniques
Authors:
Open Access
- 9 July 2021
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (7) , e0254178
Abstract
Boosting techniques from the field of statistical learning have grown to be a popular tool for estimating and selecting predictor effects in various regression models and can roughly be separated in two general approaches, namely gradient boosting and likelihood-based boosting. An extensive framework has been proposed in order to fit generalized mixed models based on boosting, however for the case of cluster-constant covariates likelihood-based boosting approaches tend to mischoose variables in the selection step leading to wrong estimates. We propose an improved boosting algorithm for linear mixed models, where the random effects are properly weighted, disentangled from the fixed effects updating scheme and corrected for correlations with cluster-constant covariates in order to improve quality of estimates and in addition reduce the computational effort. The method outperforms current state-of-the-art approaches from boosting and maximum likelihood inference which is shown via simulations and various data examples.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (Projekt WA 4249/2-1)
- Volkswagen Foundation (Freigeist Fellowship)
This publication has 34 references indexed in Scilit:
- Likelihood-Based Boosting in Binary and Ordinal Random Effects ModelsJournal of Computational and Graphical Statistics, 2013
- Regularization for Generalized Additive Mixed Models by Likelihood-based BoostingMethods of Information in Medicine, 2012
- On the behaviour of marginal and conditional AIC in linear mixed modelsBiometrika, 2010
- Generalized Linear Mixed Models Based on Boosting2009
- A boosting approach to flexible semiparametric mixed modelsStatistics in Medicine, 2006
- Multivariate Statistical Modelling Based on Generalized Linear Models.Journal of the American Statistical Association, 1996
- Primary biliary cirrhosis: Prediction of short-term survival based on repeated patient visitsHepatology, 1994
- A Comparison of GCV and GML for Choosing the Smoothing Parameter in the Generalized Spline Smoothing ProblemThe Annals of Statistics, 1985
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- A Time Series Approach To Numerical DifferentiationTechnometrics, 1974