Constrained monotone EM algorithms for finite mixture of multivariate Gaussians

DOI10.1016/j.csda.2006.10.011zbMath1445.62116MaRDI QIDQ1020213

Salvatore Ingrassia, Roberto Rocci

Publication date: 29 May 2009

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2006.10.011

zbMATH Keywords

monotonicity; EM algorithm; eigenvalues; mixture models

Mathematics Subject Classification ID

62-08: Computational methods for problems pertaining to statistics

62H12: Estimation in multivariate analysis

62H30: Classification and discrimination; cluster analysis (statistical aspects)

Related Items

Unnamed Item, Finite Mixture of Linear Regression Models: An Adaptive Constrained Approach to Maximum Likelihood Estimation, Maximum likelihood estimation in constrained parameter spaces for mixtures of factor analyzers, Avoiding spurious local maximizers in mixture modeling, Multivariate mixture modeling using skew-normal independent distributions, Comments on: ``Model-based clustering and classification with non-normal mixture distributions, Local statistical modeling via a cluster-weighted approach with elliptical distributions, A fast algorithm for robust constrained clustering, Robust estimation of mixtures of regressions with random covariates, via trimming and constraints, Bayesian analysis of skew-normal independent linear mixed models with heterogeneity in the random-effects population, Root selection in normal mixture models, Degeneracy of the EM algorithm for the MLE of multivariate Gaussian mixtures and dynamic constraints, Editorial: Advances in mixture models, The joint role of trimming and constraints in robust estimation for mixtures of Gaussian factor analyzers, A globally convergent algorithm for Lasso-penalized mixture of linear regression models, Addressing overfitting and underfitting in Gaussian model-based clustering, Clusterwise linear regression modeling with soft scale constraints, Robust, fuzzy, and parsimonious clustering, based on mixtures of factor analyzers, Multivariate response and parsimony for Gaussian cluster-weighted models, Robust clustering in regression analysis via the contaminated Gaussian cluster-weighted model, A computational strategy for doubly smoothed MLE exemplified in the normal mixture model, Parsimonious mixtures of multivariate contaminated normal distributions, The REBMIX Algorithm for the Multivariate Finite Mixture Estimation

Cites Work

• Unnamed Item
• Unnamed Item
• A constrained formulation of maximum-likelihood estimation for normal mixture distributions
• Degeneracy in the maximum likelihood estimation of univariate Gaussian mixtures with EM.
• A likelihood-based constrained algorithm for multivariate normal mixture models
• Maximum likelihood estimation via the ECM algorithm: A general framework
• Degeneracy in the Maximum Likelihood Estimation of Univariate Gaussian Mixtures for Grouped Data and Behaviour of the EM Algorithm
• An inequality with application to multivariate analysis
• Model-Based Gaussian and Non-Gaussian Clustering
• Penalized Maximum Likelihood Estimator for Normal Mixtures
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Iterative Solution Methods