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

Correspondence analysis of contingency tables.

M A Moussa1, B A Ouda

  • 1Faculty of Medicine, Kuwait University.

Computer Methods and Programs in Biomedicine
|September 1, 1988
PubMed
Summary

This study introduces correspondence analysis for multidimensional representation of contingency tables. It optimizes variable weights and visualizes relationships for better data interpretation.

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

Histopathological effects of azithromycin on broilers: immune system alterations and apoptotic changes.

British poultry science·2025
Same author

Prognostic significance of microRNA 17-92 cluster expression in Egyptian chronic lymphocytic leukemia patients.

Journal of the Egyptian National Cancer Institute·2021
Same author

Rational design and electrical study of conducting bionanocomposites hydrogel based on chitosan and silver nanoparticles.

International journal of biological macromolecules·2019
Same author

Clustering of trisomy 18 in Kuwait: Genetic predisposition or environmental?

Annals of Saudi medicine·2007
Same author

Plasma leptin concentration in patients with Type 2 diabetes: relationship to cardiovascular disease risk factors and insulin resistance.

Diabetic medicine : a journal of the British Diabetic Association·2005
Same author

Associations of plasma homocysteine concentration in subjects with type 2 diabetes mellitus.

Acta diabetologica·2002

Area of Science:

  • Statistics
  • Data Analysis
  • Multivariate Analysis

Background:

  • Contingency tables are widely used to represent categorical data.
  • Understanding the complex dependencies between row and column variables is crucial.
  • Existing methods may not fully capture multidimensional relationships.

Purpose of the Study:

  • To present a comprehensive correspondence analysis method for contingency tables.
  • To enhance the interpretation of row-column variable dependencies.
  • To provide a robust tool for multidimensional data representation.

Main Methods:

  • Correspondence analysis for multidimensional representation.
  • Iterative optimization for estimating optimal weights.
  • Canonical correlation maximization.
  • Discriminability testing of scoring schemes.
  • Contribution evaluation of categories per dimension.
  • Symmetric graphical representation of row and column points.

Main Results:

  • Optimal weights are estimated to maximize canonical correlation.
  • The discriminability of the scoring scheme is effectively tested.
  • Relative contributions of categories to each dimension are evaluated.
  • Simultaneous symmetric graphical representations are generated.

Conclusions:

  • The proposed correspondence analysis method effectively represents multidimensional dependencies in contingency tables.
  • The method is versatile, applicable to both two-way and multi-way tables.
  • It offers enhanced data visualization and interpretation capabilities.

Related Experiment Videos