Volume 38, Issue 1

Model‐based clustering of longitudinal data

Paul D. McNicholas

Corresponding Author

E-mail address: pmcnicho@uoguelph.ca

Department of Mathematics & Statistics, University of Guelph, Guelph, Ontario, Canada N1G 2W1

Department of Mathematics & Statistics, University of Guelph, Guelph, Ontario, Canada N1G 2W1.Search for more papers by this author
T. Brendan Murphy

School of Mathematical Sciences, University College Dublin, Belfield, Dublin 4, Ireland

Search for more papers by this author
First published: 26 January 2010
Citations: 11

Abstract

en

A new family of mixture models for the model‐based clustering of longitudinal data is introduced. The covariance structures of eight members of this new family of models are given and the associated maximum likelihood estimates for the parameters are derived via expectation–maximization (EM) algorithms. The Bayesian information criterion is used for model selection and a convergence criterion based on the Aitken acceleration is used to determine the convergence of these EM algorithms. This new family of models is applied to yeast sporulation time course data, where the models give good clustering performance. Further constraints are then imposed on the decomposition to allow a deeper investigation of the correlation structure of the yeast data. These constraints greatly extend this new family of models, with the addition of many parsimonious models. The Canadian Journal of Statistics 38:153–168; 2010 © 2010 Statistical Society of Canada

Abstract

fr

Nous présentons une nouvelle famille de modèles de mélanges de regroupement, à l'aide de modèles, pour des données longitudinales. La structure de covariance de huit membres de cette nouvelle famille de modèles est donnée et les estimateurs du maximum de vraisemblance associés aux paramètres sont obtenus en utilisant les algorithmes espérance‐maximisation (EM). Le critère d'information bayésien (BIC) est utilisé pour choisir le modèle et un critère de convergence basé sur l'accélération d'Aitken est utilisé pour déterminer la convergence de ces algorithmes EM. Cette nouvelle famille de modèles est appliquée sur les données de décours temporel de la sporulation de levures. Ces modèles sont performants pour faire les regroupements. Des contraintes additionnelles sont aussi imposées sur la décomposition afin d'examiner en plus de profondeur la structure de corrélation dans des données de levures. Ces contraintes généralisent grandement cette nouvelle famille de modèles avec l'ajout de modèles plus parcimonieux. La revue canadienne de statistique 38: 153–168; 2010 © 2010 Société statistique du Canada

Number of times cited according to CrossRef: 11

  • Model‐based clustering and analysis of life history data, Journal of the Royal Statistical Society: Series A (Statistics in Society), 10.1111/rssa.12575, 183, 3, (1231-1251), (2020).
  • Modeling tree diameters using mixtures of skewed Student’s t and related distributions , Canadian Journal of Forest Research, 10.1139/cjfr-2020-0008, (1-11), (2020).
  • Exploring the longitudinal dynamics of herd BVD antibody test results using model-based clustering, Scientific Reports, 10.1038/s41598-019-47339-6, 9, 1, (2019).
  • Insight Into Individual Differences in Emotion Dynamics With Clustering, Assessment, 10.1177/1073191119873714, (107319111987371), (2019).
  • undefined, 2017 Artificial Intelligence and Robotics (IRANOPEN), 10.1109/RIOS.2017.7956464, (182-187), (2017).
  • Model-Based Clustering, Journal of Classification, 10.1007/s00357-016-9211-9, 33, 3, (331-373), (2016).
  • Model-based clustering based on sparse finite Gaussian mixtures, Statistics and Computing, 10.1007/s11222-014-9500-2, 26, 1-2, (303-324), (2014).
  • Dimension Reduction in Clustering, Wiley StatsRef: Statistics Reference Online, 10.1002/9781118445112, (1-7), (2014).
  • The impact of covariance misspecification in multivariate Gaussian mixtures on estimation and inference: an application to longitudinal modeling, Statistics in Medicine, 10.1002/sim.5729, 32, 16, (2790-2803), (2013).
  • Unbundling Technology Adoption and TFP at the Firm Level - Do Intangibles Matter?, SSRN Electronic Journal, 10.2139/ssrn.2202046, (2013).
  • Bibliography, Cluster Analysis, undefined, (289-320), (2011).

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.