Multivariate linear regression with non-normal errors: a solution based on mixture models

DOI10.1007/S11222-010-9190-3zbMath1221.62106OpenAlexW2084809030MaRDI QIDQ637985

Giuliano Galimberti, Gabriele Soffritti

Publication date: 8 September 2011

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11222-010-9190-3

zbMATH Keywords

EM algorithmmodel selection criterion

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Estimation in multivariate analysis (62H12) Linear regression; mixed models (62J05) Monte Carlo methods (65C05)

Related Items (17)

Multivariate response and parsimony for Gaussian cluster-weighted models ⋮ Bayesian linear regression models with flexible error distributions ⋮ A multivariate linear regression analysis using finite mixtures of \(t\) distributions ⋮ Multivariate cluster-weighted models based on seemingly unrelated linear regression ⋮ Using mixtures in seemingly unrelated linear regression models with non-normal errors ⋮ Two-layer EM algorithm for ALD mixture regression models: a new solution to composite quantile regression ⋮ Hidden truncation hyperbolic distributions, finite mixtures thereof, and their application for clustering ⋮ Coverage probabilities of confidence intervals for the slope parameter of linear regression model when the error term is not normally distributed ⋮ Multivariate cluster weighted models using skewed distributions ⋮ Graphical and Computational Tools to Guide Parameter Choice for the Cluster Weighted Robust Model ⋮ Seemingly unrelated clusterwise linear regression for contaminated data ⋮ Seemingly unrelated clusterwise linear regression ⋮ Modelling the role of variables in model-based cluster analysis ⋮ Adaptive robust regression with continuous Gaussian scale mixture errors ⋮ Measuring sample quality with diffusions ⋮ Bayesian variable selection in linear regression models with non-normal errors ⋮ Heavy or semi-heavy tail, that is the question

Uses Software

• mclust
• R
• flexmix
• bootstrap

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A maximum likelihood methodology for clusterwise linear regression
• Identifiability of finite mixtures of multinomial logit models with varying and fixed effects
• The use of mixtures for dealing with non-normal regression errors
• Variable selection in model-based clustering: a general variable role modeling
• Model-based methods to identify multiple cluster structures in a data set
• Model selection and Akaike's information criterion (AIC): The general theory and its analytical extensions
• Estimating the dimension of a model
• Fixed point clusters for linear regression: Computation and comparison
• Identifiability of models for clusterwise linear regression
• Enhanced model-based clustering, density estimation, and discriminant analysis software:\newline MCLUST
• Local influence in multivariate elliptical linear regression models
• Statistical inference for location and scale of elliptically contoured models with monotone missing data
• Variable Selection for Clustering with Gaussian Mixture Models
• The EM Algorithm and Extensions, 2E
• Estimation of the parameters of a regression model with a multivariate t error variable
• Maximum likelihood estimates of the parameters of a mixture of two regression lines
• Bayesian and Non-Bayesian Analysis of the Regression Model with Multivariate Student-t Error Terms
• How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis
• Statistical Applications of the Multivariate Skew Normal Distribution
• Model-Based Gaussian and Non-Gaussian Clustering
• Bayesian Robust Multivariate Linear Regression With Incomplete Data
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Finite mixture models
• Distributions Generated by Perturbation of Symmetry with Emphasis on a Multivariate Skewt-Distribution
• Influence Diagnostics for Elliptical Multivariate Linear Regression Models
• Multivariate Linear Regression Model with Elliptically Contoured Distributed Errors and Monotone Missing Dependent Variables
• On the Identifiability of Finite Mixtures
• Variable Selection for Model-Based Clustering
• A cautionary note on likelihood ratio tests in mixture models

This page was built for publication: Multivariate linear regression with non-normal errors: a solution based on mixture models