 A scalable and efficient covariate selection criterion for mixed effects regression models with unknown random effects structureRadu V. Craiu and Thierry Duchesne Computational Statistics & Data Analysis, 2018, vol. 117, issue C, 154-161 Abstract: A new model selection criterion for mixed effects regression models is introduced. The criterion is computable even when the model is fitted with a two-step method or when the structure and the distribution of the random effects are unknown. The criterion is especially useful in the early stage of the model building process when one needs to decide which covariates should be included in a mixed effects regression model, but has no knowledge of the random effect structure. This is particularly relevant in substantive fields where variable selection is guided by information criteria rather than regularization. The calculation of the criterion requires only the evaluation of cluster-level log-likelihoods and does not rely on heavy numerical integration. Theoretical and numerical arguments are used to justify the method and its usefulness is illustrated by analysing data from a youth behaviour study. Keywords: Akaike information criterion; Generalized linear mixed model; h-likelihood; Random coefficient model; Two-stage estimation; Variable selection (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:117:y:2018:i:c:p:154-161 DOI: 10.1016/j.csda.2017.07.011 Access Statistics for this article Computational Statistics & Data Analysis is currently edited by S.P. Azen More articles in Computational Statistics & Data Analysis from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.