On Using Principal Components Before Separating a Mixture of Two Multivariate Normal Distributions

DOI10.2307/2347949zbMath0538.62050MaRDI QIDQ3324854

Wei-Chien Chang

Publication date: 1983

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

Full work available at URL: https://doi.org/10.2307/2347949

zbMATH Keywords

clustering; eigenvalues; distance; scaling; principal components; mixture of two multivariate normal distributions; selection of components

Mathematics Subject Classification ID

62H25: Factor analysis and principal components; correspondence analysis

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

Related Items

A simulation study of the use of principal components in linear discriminant analysis, Component reduction in linear discriminant analysis, Modelling high-dimensional data by mixtures of factor analyzers, Theoretical and practical considerations on the convergence properties of the Fisher-EM algorithm, Finite mixtures of matrix normal distributions for classifying three-way data, Variable selection and updating in model-based discriminant analysis for high dimensional data with food authenticity applications, Order-constrained solutions in \(K\)-means clustering: even better than being globally optimal, Optimal classification for time-course gene expression data using functional data analysis, Use of SVD-based probit transformation in clustering gene expression profiles, Density-based silhouette diagnostics for clustering methods, Better alternatives to current methods of scaling and weighting data for cluster analysis