Location and scale mixtures of Gaussians with flexible tail behaviour: properties, inference and application to multivariate clustering

DOI10.1016/j.csda.2015.04.008zbMath1468.62210OpenAlexW2079256353WikidataQ62763506 ScholiaQ62763506MaRDI QIDQ1663203

Florence Forbes, Darren Wraith

Publication date: 21 August 2018

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

Full work available at URL: https://doi.org/10.1016/j.csda.2015.04.008

zbMATH Keywords

EM algorithmcovariance matrix decompositionrobust clusteringmultivariate generalized hyperbolic distributionGaussian location and scale mixture

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Computational methods for problems pertaining to statistics (62-08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Characterization and structure theory for multivariate probability distributions; copulas (62H05)

Related Items (15)

Skew selection for factor stochastic volatility models ⋮ Autoregressive processes with generalized hyperbolic innovations ⋮ Inverse regression approach to robust nonlinear high-to-low dimensional mapping ⋮ ECM algorithm for estimating vector ARMA model with variance gamma distribution and possible unbounded density ⋮ GTL regression: a linear model with skewed and thick-tailed disturbances ⋮ The skewness of mean-variance normal mixtures ⋮ A multivariate skew-normal-Tukey-\(h\) distribution ⋮ A classification method for binary predictors combining similarity measures and mixture models ⋮ Flexible Modelling via Multivariate Skew Distributions ⋮ Optimal tests for elliptical symmetry: specified and unspecified location ⋮ A flexible class of parametric distributions for Bayesian linear mixed models ⋮ A mixture of coalesced generalized hyperbolic distributions ⋮ Variable Selection for Skewed Model-Based Clustering: Application to the Identification of Novel Sleep Phenotypes ⋮ An overview of skew distributions in model-based clustering ⋮ Robust finite mixture modeling of multivariate unrestricted skew-normal generalized hyperbolic distributions

Uses Software

• R
• mixtools
• Emmixuskew
• MixGHD

Cites Work

• Unnamed Item
• Unnamed Item
• Estimating common principal components in high dimensions
• A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweight: application to robust clustering
• Multivariate mixture modeling using skew-normal independent distributions
• Robust mixture modeling based on scale mixtures of skew-normal distributions
• Semiparametric mixtures of regressions
• Clustering with mixtures of log-concave distributions
• Rejoinder to the discussion of ``Model-based clustering and classification with non-normal mixture distributions
• Model comparison of coordinate-free multivariate skewed distributions with an application to stochastic frontiers
• On mixtures of skew normal and skew \(t\)-distributions
• A robust extension of the bivariate Birnbaum-Saunders distribution and associated inference
• Finite mixtures of multivariate skew \(t\)-distributions: some recent and new results
• Orthogonal Stiefel manifold optimization for eigen-decomposed covariance parameter estimation in mixture models
• Flexible mixture modelling using the multivariate skew-\(t\)-normal distribution
• Choosing initial values for the EM algorithm for finite mixtures
• Multivariate distribution models with generalized hyperbolic margins
• High-dimensional data clustering
• Statistical properties of the generalized inverse Gaussian distribution
• An EM type algorithm for maximum likelihood estimation of the normal-inverse Gaussian distribution
• Learning from incomplete data via parameterized \(t\) mixture models through eigenvalue decomposition
• Mixtures of common \(t\)-factor analyzers for modeling high-dimensional data with missing values
• Mixtures of regressions with predictor-dependent mixing proportions
• Multivariate skew-normal generalized hyperbolic distribution and its properties
• On fast supervised learning for normal mixture models with missing information
• Finite mixture and Markov switching models.
• Normal Variance-Mean Mixtures and z Distributions
• Normal Inverse Gaussian Distributions and Stochastic Volatility Modelling
• A new class of multivariate skew distributions with applications to bayesian regression models
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Robustness Properties of k Means and Trimmed k Means
• Distributions Generated by Perturbation of Symmetry with Emphasis on a Multivariate Skewt-Distribution
• An Algorithm for Simultaneous Orthogonal Transformation of Several Positive Definite Symmetric Matrices to Nearly Diagonal Form
• Multivariate T-Distributions and Their Applications
• A mixture of generalized hyperbolic distributions
• A general class of multivariate skew-elliptical distributions

This page was built for publication: Location and scale mixtures of Gaussians with flexible tail behaviour: properties, inference and application to multivariate clustering