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

Estimating pattern similarity for correlation matrices from differing neuropsychiatric populations

P C Fowler1, S N MacCiocchi, J D Ranseen

  • 1Department of Psychiatric Medicine, University of Virginia Health Sciences Center, Charlottesville 22901.

Psychological Reports
|December 1, 1993
PubMed
Summary

This study presents a new method to compare correlation matrices from different patient groups. It helps determine if data can be combined for more robust neuropsychological research and model diagnostics.

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

Assessing risk and harm: the convergence of ethical and empirical considerations.

Archives of physical medicine and rehabilitation·2002
Same author

Short-term neuropsychological outcome following Gamma Knife radiosurgery for arteriovenous malformations: a preliminary report.

Applied neuropsychology·1999
Same author

Head injury--a survey of current practices in preventive health care counselling.

Brain injury·1998
Same author

Ischemic stroke: relation of age, lesion location, and initial neurologic deficit to functional outcome.

Archives of physical medicine and rehabilitation·1998
Same author

NEO PI-R profiles of adults with attention deficit disorder.

Assessment·1998
Same author

Outcome after mild head injury.

Clinics in sports medicine·1998

Area of Science:

  • Neuropsychology
  • Psychometrics
  • Statistical analysis

Background:

  • Assessing pattern similarity in correlation matrices is crucial for combining data from distinct populations.
  • Confirmatory factor analysis (CFA) of neuropsychological traits often yields correlation matrices that require evaluation before aggregation.
  • Clinically significant differences between populations necessitate careful examination of matrix similarity.

Purpose of the Study:

  • To introduce and illustrate a novel method for evaluating pattern similarity between correlation matrices.
  • To assess the suitability of aggregating correlation matrices from populations with known clinical differences.
  • To enhance model diagnostics in applied neuropsychology research.

Main Methods:

  • Utilized existing data from published confirmatory factor analyses of neuropsychological traits.

Related Experiment Videos

  • Developed and applied two distinct methods to assess the similarity of correlation matrices.
  • Focused on evaluating whether matrices are sufficiently similar for justified aggregation into a single composite matrix.

    • Main Results:

    • The presented methods provide a quantitative approach to assessing pattern similarity in correlation matrices.
    • The study demonstrates how to evaluate the comparability of matrices derived from clinically distinct populations.
    • The findings support the judicious aggregation of correlation matrices when similarity criteria are met.

    Conclusions:

    • The proposed method offers a valuable tool for applied neuropsychology, improving data integration.
    • Enhanced model diagnostics can be achieved by employing this similarity assessment procedure.
    • This approach facilitates more reliable composite matrix construction and subsequent analyses in neuropsychological research.