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

Exploratory factor analysis: its role in item analysis.

R L Gorsuch1

  • 1Graduate School of Psychology, Fuller Theological Seminary, Pasadena, CA 91101, USA.

Journal of Personality Assessment
|January 1, 1997
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

Second Stratum Personality Factors Defined In The Questionnaire Realm By The 16 P.F.

Multivariate behavioral research·2016
Same author

R. B. Cattell: An Integration of Psychology and Ethics.

Multivariate behavioral research·2016
Same author

Common Factor Analysis versus Component Analysis: Some Well and Little Known Facts.

Multivariate behavioral research·2016
Same author

Factor analysis of four measures of prefrontal lobe functioning.

Archives of clinical neuropsychology : the official journal of the National Academy of Neuropsychologists·2003
Same author

Replication of the factor structure of the Wechsler Adult Intelligence Scale--Third Edition with a Canadian sample.

Psychological assessment·2001
Same author

Lifelong estrogen exposure and cognitive performance in elderly women.

Brain and cognition·1999

The default "Little Jiffy" method for exploratory item factor analysis is inadequate due to item characteristics. Improved procedures and scale evaluation methods are presented for more reliable factor analysis.

Area of Science:

  • Psychometrics
  • Statistical Analysis
  • Quantitative Psychology

Background:

  • Traditional exploratory item factor analysis (EFA) methods, such as the default 'Little Jiffy' in many statistical packages, are increasingly inadequate.
  • Specific item characteristics like low reliability, unwanted covariance, and the presence of a general factor complicate standard EFA.
  • Existing methods often produce an excessive number of factors and fail to identify a general factor, leading to non-replicable results.

Purpose of the Study:

  • To address the limitations of standard EFA procedures for item analysis.
  • To present more appropriate methods for exploratory item factor analysis that account for specific item characteristics.
  • To provide guidance on sample selection, sample size determination, and item selection for scale development.

Related Experiment Videos

Main Methods:

  • Evaluation of the 'Little Jiffy' procedure against more advanced factor analytic techniques.
  • Development and presentation of alternative EFA procedures designed to mitigate issues of low reliability and general factors.
  • Introduction of a novel method for evaluating proposed scales by correlating them with extracted factors, avoiding biased correlations with total or factor scores.

Main Results:

  • The default 'Little Jiffy' procedure often yields an over-extraction of factors and incorrectly excludes general factors, compromising replicability.
  • The proposed alternative procedures effectively address common problems in EFA, leading to more accurate and replicable factor structures.
  • The new scale evaluation procedure provides less biased estimates of scale-factor relationships compared to traditional methods.

Conclusions:

  • The 'Little Jiffy' method is no longer sufficient for robust exploratory item factor analysis.
  • Adoption of the presented advanced procedures and evaluation techniques is recommended for improved scale development and factor analysis.
  • Understanding the interplay between item characteristics and factor analytic methods is crucial for valid psychometric research.