A fast algorithm for clusterwise linear regression

DOI10.1007/BF02249940zbMath0485.65030MaRDI QIDQ1164376

Helmuth Späth

Publication date: 1982

Published in: Computing (Search for Journal in Brave)

zbMATH Keywords

least squares; fast algorithm; cluster analysis; clusterwise linear regression; minimum variance criterion

Mathematics Subject Classification ID

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

62J05: Linear regression; mixed models

65F20: Numerical solutions to overdetermined systems, pseudoinverses

65C99: Probabilistic methods, stochastic differential equations

Related Items

A maximum likelihood methodology for clusterwise linear regression, An \(M\)-estimation-based procedure for determining the number of regression models in regression clustering, Linear grouping using orthogonal regression, A three-way clusterwise multidimensional unfolding procedure for the spatial representation of context dependent preferences, Algorithm: Clusterwise linear least absolute deviations regression, A fast algorithm for clusterwise linear absolute deviations regression, A mathematical programming approach to clusterwise regression model and its extensions, A general estimation procedure based on group means, A consistent procedure for determining the number of clusters in regression clustering, Robust Linear Clustering

Uses Software

• AS 75
• Algorithm 39

Cites Work

• Unnamed Item
• Correction to: Algorithm 39. Clusterwise linear regression
• Clusterwise linear regression
• Reorthogonalization and Stable Algorithms for Updating the Gram-Schmidt QR Factorization
• Numerically Stable Methods for Updating Regressions
• Least Squares Computations by Givens Transformations Without Square Roots