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

Identifying criterion-related patterns of predictor scores using multiple regression.

Mark L Davison1, Ernest C Davenport

  • 1Department of Educational Psychology, University of Minnesota, Minneapolis, Minnesota 55455, USA. mld@umn.edu

Psychological Methods
|January 18, 2003
PubMed
Summary

This study introduces a pattern recognition method using multiple regression to identify predictor score patterns linked to high criterion variable scores. It also details methods for estimating and validating the variation attributed to these criterion patterns.

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

A Multidimensional Model to Facilitate Within Person Comparison of Attributes.

Psychometrika·2026
Same author

Validating a Reading Comprehension Assessment for College Students: Preliminary Findings.

Journal of psycholinguistic research·2025
Same author

A Multidimensional Model to Facilitate Within Person Comparison of Attributes.

Psychometrika·2024
Same author

MOCCA-College: Preliminary Validity Evidence of a Cognitive Diagnostic Reading Comprehension Assessment.

Journal of learning disabilities·2022
Same author

Regression with reduced rank predictor matrices: A model of trade-offs.

Psychological methods·2022
Same author

Linear equality constraints: Reformulations of criterion related profile analysis with extensions to moderated regression for multiple groups.

Psychological methods·2022

Area of Science:

  • Psychometrics
  • Quantitative Psychology
  • Educational Measurement

Background:

  • Identifying specific patterns of predictor variables associated with outcomes is crucial in various fields, including vocational interests and academic achievement.
  • Existing methods may not fully capture the complex relationships between multiple predictors and a criterion variable.
  • The need for robust statistical procedures to define and validate such patterns is evident.

Purpose of the Study:

  • To present a novel multiple regression-based pattern recognition procedure for identifying criterion patterns.
  • To describe methods for estimating the proportion of variance explained by the identified criterion pattern.
  • To outline the use of cross-validation for assessing the stability of criterion patterns across different samples.

Main Methods:

Related Experiment Videos

  • A multiple regression approach is employed to identify a specific pattern of predictor scores.
  • This identified pattern is termed the 'criterion pattern'.
  • Subsequent regression and cross-validation techniques are used to estimate and validate the variation attributable to the criterion pattern.

Main Results:

  • The study demonstrates a procedure to identify a distinct criterion pattern from predictor scores.
  • Methods are provided to quantify the variance explained by this criterion pattern.
  • Cross-validation results offer insights into the generalizability of the criterion pattern.

Conclusions:

  • The described multiple regression-based procedure effectively identifies and validates criterion patterns.
  • This method provides a framework for understanding the contribution of specific predictor combinations to criterion variables.
  • Further discussion addresses the invariance and interpretation of criterion patterns in diverse contexts.