Gennclus: New models for general nonhierarchical clustering analysis

Wayne Desarbo

Research output: Contribution to journalArticle

68 Citations (Scopus)

Abstract

A general class of nonhierarchical clustering models and associated algorithms for fitting them are presented. These (metric) clustering models generalize the Shepard-Arabie Additive Clusters model in allowing for: (1). either overlapping or nonoverlapping clusters; (2). either symmetric (one-way clustering) or nonsymmetric (two-way clustering) proximities (input data); and, (3). either symmetric or diagonal weights. The GENNCLUS algorithms utilize alternating least-squares methods combining ordinary and constrained least-squares, nonlinear constrained mathematical programming, and combinatorial optimization techniques in estimating model parameters. In addition to developing the mathematical bases of these models, a comprehensive set of Monte Carlo simulations of the different models is reported. Two applications concerning brand-switching data and celebrity-brand proximities are discussed. Finally, extensions to three-way models, nonmetric analyses, and other model specifications are provided.

Original languageEnglish (US)
Pages (from-to)449-475
Number of pages27
JournalPsychometrika
Volume47
Issue number4
DOIs
StatePublished - Dec 1 1982

Fingerprint

Clustering Analysis
Cluster Analysis
Least-Squares Analysis
Clustering
Proximity
Model
Theoretical Models
Alternating Least Squares
Constrained Least Squares
Model Specification
Weights and Measures
Combinatorial Optimization
Mathematical Programming
Least Square Method
Mathematical programming
Combinatorial optimization
Optimization Techniques
Overlapping
Monte Carlo Simulation
Metric

All Science Journal Classification (ASJC) codes

  • Psychology(all)
  • Applied Mathematics

Cite this

Desarbo, Wayne. / Gennclus : New models for general nonhierarchical clustering analysis. In: Psychometrika. 1982 ; Vol. 47, No. 4. pp. 449-475.
@article{044610ca65e54249a5417e793ad9d63c,
title = "Gennclus: New models for general nonhierarchical clustering analysis",
abstract = "A general class of nonhierarchical clustering models and associated algorithms for fitting them are presented. These (metric) clustering models generalize the Shepard-Arabie Additive Clusters model in allowing for: (1). either overlapping or nonoverlapping clusters; (2). either symmetric (one-way clustering) or nonsymmetric (two-way clustering) proximities (input data); and, (3). either symmetric or diagonal weights. The GENNCLUS algorithms utilize alternating least-squares methods combining ordinary and constrained least-squares, nonlinear constrained mathematical programming, and combinatorial optimization techniques in estimating model parameters. In addition to developing the mathematical bases of these models, a comprehensive set of Monte Carlo simulations of the different models is reported. Two applications concerning brand-switching data and celebrity-brand proximities are discussed. Finally, extensions to three-way models, nonmetric analyses, and other model specifications are provided.",
author = "Wayne Desarbo",
year = "1982",
month = "12",
day = "1",
doi = "10.1007/BF02293709",
language = "English (US)",
volume = "47",
pages = "449--475",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "4",

}

Gennclus : New models for general nonhierarchical clustering analysis. / Desarbo, Wayne.

In: Psychometrika, Vol. 47, No. 4, 01.12.1982, p. 449-475.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gennclus

T2 - New models for general nonhierarchical clustering analysis

AU - Desarbo, Wayne

PY - 1982/12/1

Y1 - 1982/12/1

N2 - A general class of nonhierarchical clustering models and associated algorithms for fitting them are presented. These (metric) clustering models generalize the Shepard-Arabie Additive Clusters model in allowing for: (1). either overlapping or nonoverlapping clusters; (2). either symmetric (one-way clustering) or nonsymmetric (two-way clustering) proximities (input data); and, (3). either symmetric or diagonal weights. The GENNCLUS algorithms utilize alternating least-squares methods combining ordinary and constrained least-squares, nonlinear constrained mathematical programming, and combinatorial optimization techniques in estimating model parameters. In addition to developing the mathematical bases of these models, a comprehensive set of Monte Carlo simulations of the different models is reported. Two applications concerning brand-switching data and celebrity-brand proximities are discussed. Finally, extensions to three-way models, nonmetric analyses, and other model specifications are provided.

AB - A general class of nonhierarchical clustering models and associated algorithms for fitting them are presented. These (metric) clustering models generalize the Shepard-Arabie Additive Clusters model in allowing for: (1). either overlapping or nonoverlapping clusters; (2). either symmetric (one-way clustering) or nonsymmetric (two-way clustering) proximities (input data); and, (3). either symmetric or diagonal weights. The GENNCLUS algorithms utilize alternating least-squares methods combining ordinary and constrained least-squares, nonlinear constrained mathematical programming, and combinatorial optimization techniques in estimating model parameters. In addition to developing the mathematical bases of these models, a comprehensive set of Monte Carlo simulations of the different models is reported. Two applications concerning brand-switching data and celebrity-brand proximities are discussed. Finally, extensions to three-way models, nonmetric analyses, and other model specifications are provided.

UR - http://www.scopus.com/inward/record.url?scp=34250225890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250225890&partnerID=8YFLogxK

U2 - 10.1007/BF02293709

DO - 10.1007/BF02293709

M3 - Article

AN - SCOPUS:34250225890

VL - 47

SP - 449

EP - 475

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -