Exploration of model misspecification in latent class methods for longitudinal data: correlation structure matters

DOI10.1002/sim.9730zbMATH Open1545.62476MaRDI QIDQ6625783

Megan L. Neely, Jane F. Pendergast, Natalia O. Dmitrieva, Carl F. Pieper, Bida Gu

Publication date: 28 October 2024

Published in: Statistics in Medicine (Search for Journal in Brave)

zbMATH Keywords

parameter biasclass enumerationgrowth mixture modelingcorrelation structure misspecificationcovariate pattern mixture modelslatent class trajectory analysis

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Longitudinal data analysis using generalized linear models
• Covariance pattern mixture models for the analysis of multivariate heterogeneous longitudinal data
• Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions
• An entropy criterion for assessing the number of clusters in a mixture model
• Likelihood of a model and information criteria
• Estimating the dimension of a model
• Two new unconstrained optimization algorithms which use function and gradient values
• Testing the number of components in a normal mixture
• Bias of the corrected AIC criterion for underfitted regression and time series models
• An Adaptive Nonlinear Least-Squares Algorithm
• Further analysis of the data by Akaike's information criterion and the finite corrections
• Finite Mixture Modeling with Mixture Outcomes Using the EM Algorithm
• Bayes Factors
• A new look at the statistical model identification

This page was built for publication: Exploration of model misspecification in latent class methods for longitudinal data: correlation structure matters