Mixtures of skew-t factor analyzers

DOI10.1016/J.CSDA.2014.03.012zbMATH Open1506.62132arXiv1305.4301OpenAlexW2046343360MaRDI QIDQ1623604FDOQ1623604

Authors: Paula M. Murray, Ryan P. Browne, Paul D. McNicholas 

Publication date: 23 November 2018

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

Abstract: In this paper, we introduce a mixture of skew-t factor analyzers as well as a family of mixture models based thereon. The mixture of skew-t distributions model that we use arises as a limiting case of the mixture of generalized hyperbolic distributions. Like their Gaussian and t-distribution analogues, our mixture of skew-t factor analyzers are very well-suited to the model-based clustering of high-dimensional data. Imposing constraints on components of the decomposed covariance parameter results in the development of eight flexible models. The alternating expectation-conditional maximization algorithm is used for model parameter estimation and the Bayesian information criterion is used for model selection. The models are applied to both real and simulated data, giving superior clustering results compared to a well-established family of Gaussian mixture models.

Full work available at URL: https://arxiv.org/abs/1305.4301

Recommendations

• Mixtures of restricted skew-\(t\) factor analyzers with common factor loadings
• Mixtures of factor analyzers with scale mixtures of fundamental skew normal distributions
• Mixtures of skewed matrix variate bilinear factor analyzers
• Robust mixtures of factor analysis models using the restricted multivariate skew-t distribution
• Extending mixtures of multivariate \(t\)-factor analyzers
• Extending mixtures of multivariate \(t\)-factor analyzers
• Mixtures of multivariate restricted skew-normal factor analyzer models in a Bayesian framework
• Mixtures of factor analyzers: an extension with covariates
• Extending mixtures of factor models using the restricted multivariate skew-normal distribution
• Extension of the mixture of factor analyzers model to incorporate the multivariate \(t\)-distribution

zbMATH Keywords

clusteringfactor analysishigh-dimensional datamixture modelsmodel-based clusteringMSTFAskew-\(t\) mixturesskewed mixtures

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Cites Work

• MCLUST: Software for model-based cluster analysis
• Finding Groups in Data
• Estimating the dimension of a model
• Non-Gaussian Ornstein-Uhlenbeck-based models and some of their uses in financial economics. (With discussion)
• Title not available (Why is that?)
• Serial and parallel implementations of model-based clustering via parsimonious Gaussian mixture models
• The distribution of the likelihood ratio for mixtures of densities from the one-parameter exponential family
• Maximum likelihood estimation via the ECM algorithm: A general framework
• Model-based clustering of longitudinal data
• Mixture models: theory, geometry and applications
• Detecting Features in Spatial Point Processes with Clutter via Model-Based Clustering
• Infinite divisibility of the hyperbolic and generalized inverse Gaussian distributions
• The EM Algorithm and Extensions, 2E
• A new class of multivariate skew distributions with applications to bayesian regression models
• A general class of multivariate skew-elliptical distributions
• Model-based classification using latent Gaussian mixture models
• Title not available (Why is that?)
• Extension of the mixture of factor analyzers model to incorporate the multivariate \(t\)-distribution
• Statistical properties of the generalized inverse Gaussian distribution
• Parsimonious skew mixture models for model-based clustering and classification
• Maximum likelihood estimation for multivariate skew normal mixture models
• Dimension reduction for model-based clustering via mixtures of shifted asymmetric Laplace distributions
• On mixtures of skew normal and skew \(t\)-distributions
• Dimension reduction for model-based clustering via mixtures of multivariate \(t\)-distributions
• Self-decomposability of the generalized inverse Gaussian and hyperbolic distributions
• Analytic calculations for the EM algorithm for multivariate skew-\(t\) mixture models
• Title not available (Why is that?)
• Title not available (Why is that?)
• THE POPULATION FREQUENCIES OF SPECIES AND THE ESTIMATION OF POPULATION PARAMETERS
• Flexible Class of Skew-Symmetric Distributions
• Clustering gene expression time course data using mixtures of multivariate \(t\)-distributions
• A Skew Extension of the T-Distribution, with Applications
• Finite mixtures of multivariate Poisson distributions with application
• On the Bumpy Road to the Dominant Mode
• Extending mixtures of multivariate \(t\)-factor analyzers
• A skew-normal factor model for the analysis of student satisfaction towards university courses

Cited In (61)

• Model-based clustering of non-Gaussian panel data based on skew-\(t\) distributions
• On formulations of skew factor models: skew factors and/or skew errors
• Mixtures of generalized hyperbolic distributions and mixtures of skew-\(t\) distributions for model-based clustering with incomplete data
• On fractionally-supervised classification: weight selection and extension to the multivariate \(t\)-distribution
• Asymmetric clusters and outliers: mixtures of multivariate contaminated shifted asymmetric Laplace distributions
• Bayesian inference for finite mixtures of univariate and multivariate skew-normal and skew-\(t\) distributions
• Hidden truncation hyperbolic distributions, finite mixtures thereof, and their application for clustering
• A flexible factor analysis based on the class of mean-mixture of normal distributions
• Model based clustering of high-dimensional binary data
• Mixtures of multivariate restricted skew-normal factor analyzer models in a Bayesian framework
• Model-based clustering
• A mixture of variance-gamma factor analyzers
• Variational Bayes approximations for clustering via mixtures of normal inverse Gaussian distributions
• Robust model-based clustering via mixtures of skew-\(t\) distributions with missing information
• Multivariate response and parsimony for Gaussian cluster-weighted models
• In the pursuit of sparseness: a new rank-preserving penalty for a finite mixture of factor analyzers
• Mixture model averaging for clustering
• Extending mixtures of multivariate \(t\)-factor analyzers
• Variable selection for skewed model-based clustering: application to the identification of novel sleep phenotypes
• Finite mixtures of canonical fundamental skew \(t\)-distributions. The unification of the restricted and unrestricted skew \(t\)-mixture models
• Robust skew-\(t\) factor analysis models for handling missing data
• A finite mixture approach to joint clustering of individuals and multivariate discrete outcomes
• Mixtures of skewed matrix variate bilinear factor analyzers
• Flexible factor model for handling missing data in supervised learning
• A novel mixture model using the multivariate normal mean-variance mixture of Birnbaum-Saunders distributions and its application to extrasolar planets
• A variational approximations-DIC rubric for parameter estimation and mixture model selection within a family setting
• Model-based simultaneous clustering and ordination of multivariate abundance data in ecology
• Clustering, classification, discriminant analysis, and dimension reduction via generalized hyperbolic mixtures
• Latent profile analysis with nonnormal mixtures: a Monte Carlo examination of model selection using fit indices
• A mixture factor model with applications to microarray data
• Banks' business models in the euro area: a cluster analysis in high dimensions
• A mixture of generalized hyperbolic factor analyzers
• An overview of skew distributions in model-based clustering
• Mixtures of hidden truncation hyperbolic factor analyzers
• Discussion of `Model-based clustering and classification with non-normal mixture distributions' by Lee and McLachlan
• Mixtures of common \(t\)-factor analyzers for modeling high-dimensional data with missing values
• A mixture of coalesced generalized hyperbolic distributions
• Infinite mixtures of multivariate normal-inverse Gaussian distributions for clustering of skewed data
• A mixture of generalized hyperbolic distributions
• A robust factor analysis model using the restricted skew-\(t\) distribution
• Piecewise regression mixture for simultaneous functional data clustering and optimal segmentation
• Robust clustering of multiply censored data via mixtures of \(t\) factor analyzers
• Mixtures of multivariate power exponential distributions
• Inferring food intake from multiple biomarkers using a latent variable model
• Mixtures of restricted skew-\(t\) factor analyzers with common factor loadings
• Factor probabilistic distance clustering (FPDC): a new clustering method
• Robust mixtures of factor analysis models using the restricted multivariate skew-t distribution
• Mixtures of factor analyzers with scale mixtures of fundamental skew normal distributions
• The estimation of normal mixtures with latent variables
• Mixtures of Gaussian copula factor analyzers for clustering high dimensional data
• Extending mixtures of multivariate \(t\)-factor analyzers
• Skew-normal factor analysis models with incomplete data
• Extending mixtures of factor models using the restricted multivariate skew-normal distribution
• Extension of the mixture of factor analyzers model to incorporate the multivariate \(t\)-distribution
• Distance Metrics and Clustering Methods for Mixed‐type Data
• Model-based clustering and classification using mixtures of multivariate skewed power exponential distributions
• Analysis of antibody data using skew-normal and skew-\(t\) mixture models
• Multivariate cluster weighted models using skewed distributions
• Anderson relaxation test for intrinsic dimension selection in model-based clustering
• Flexible clustering of high-dimensional data via mixtures of joint generalized hyperbolic distributions
• Unsupervised classification with a family of parsimonious contaminated shifted asymmetric Laplace mixtures

Uses Software

• mclust
• R
• PGMM
• clusfind

This page was built for publication: Mixtures of skew-\(t\) factor analyzers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1623604)