Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Stability analysis in K-means clustering.

Douglas Steinley1

  • 1Department of Psychological Sciences, 210 McAlester Hall, Columbia, MO 65211, USA. steinleyd@missouri.edu

The British Journal of Mathematical and Statistical Psychology
|May 31, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Right-sizing growth mixture models as multi-group growth and confirmatory factor models.

Behavior research methods·2025
Same author

Cognitive behavioral therapy for insomnia among heavy-drinking veterans: a randomized pilot trial.

Sleep advances : a journal of the Sleep Research Society·2025
Same author

"General Addiction Liability" Revisited.

Clinical psychological science : a journal of the Association for Psychological Science·2025
Same author

Integer programming in psychology: A review and directions for future research.

The British journal of mathematical and statistical psychology·2025
Same author

Daily associations between sleep and alcohol use among veterans: Acute and cumulative effects.

Addiction (Abingdon, England)·2025
Same author

Clustering methods: To optimize or to not optimize?

Psychological methods·2024
Same journal

Proficiency order invariance of MLE, MAP, EAP, and WLE in item response theory.

The British journal of mathematical and statistical psychology·2026
Same journal

Bias and precision in true-score estimation.

The British journal of mathematical and statistical psychology·2026
Same journal

Polychoric correlations under the assumption of elliptical latent traits.

The British journal of mathematical and statistical psychology·2026
Same journal

Regularized reduced rank regression for mixed predictor and response variables.

The British journal of mathematical and statistical psychology·2026
Same journal

A multiple-choice SDT model for cognitive diagnosis models.

The British journal of mathematical and statistical psychology·2026
Same journal

Modular item response and structural equation modelling via measurement and uncertainty preserving parametric modelling.

The British journal of mathematical and statistical psychology·2026
See all related articles

This study introduces stability analysis for K-means clustering, using local optima to reveal data structure. It enhances cluster interpretation by analyzing object co-occurrence for better insights into relationships.

Area of Science:

  • Data Science
  • Machine Learning
  • Statistics

Background:

  • K-means clustering is a widely used algorithm for partitioning data into distinct groups.
  • Traditional K-means often converges to local optima, potentially missing the global best solution.
  • Evaluating the stability and structure of clusters beyond the single best outcome is crucial for robust analysis.

Purpose of the Study:

  • To introduce a novel procedure, stability analysis, for K-means clustering.
  • To leverage information from locally optimal solutions, not just the best one.
  • To develop methods for assessing overall data structure, cluster counts, and inter-cluster relationships.

Main Methods:

  • Developing a stability analysis procedure for K-means clustering.

Related Experiment Videos

  • Constructing an object-by-object co-occurrence matrix from locally optimal solutions.
  • Clustering and reordering the co-occurrence matrix using a steepest ascent quadratic assignment procedure.
  • Creating measures to determine data set structure, number of clusters, and multidimensional cluster relationships.

    • Main Results:

    • The stability analysis procedure effectively utilizes information from local optima in K-means.
    • The co-occurrence matrix and its reordering aid in visualizing multidimensional cluster structures.
    • New measures are established for evaluating data structure, cluster identification, and inter-cluster dynamics.
    • The method provides a more comprehensive understanding of clustering outcomes.

    Conclusions:

    • Stability analysis offers a significant advancement over standard K-means by incorporating local optima.
    • The developed techniques enhance the interpretability and robustness of clustering results.
    • This approach provides valuable tools for exploring complex data structures and relationships between clusters.