How Should the Internal Structure of Personality Inventories Be Evaluated?

Personality trait inventories often perform poorly when their structure is evaluated with confirmatory factor analysis (CFA). The authors demonstrate poor CFA fit for several widely used personality measures with documented evidence of criterion-related validity but also show that some measures perf...

Full description

Saved in:
Bibliographic Details
Published in:Personality and social psychology review 2010-08, Vol.14 (3), p.332-346
Main Authors: Hopwood, Christopher J., Donnellan, M. Brent
Format: Article
Language:English
Subjects:
Bias
Biological and medical sciences
Character
Confirmatory factor analysis
Discriminant analysis
Factor Analysis, Statistical
Fundamental and applied biological sciences. Psychology
Humans
Individuality
Internal validity
Measures
Personality Inventory - statistics & numerical data
Personality psychology
Personality tests
Personality traits
Personality. Affectivity
Psychology. Psychoanalysis. Psychiatry
Psychology. Psychophysiology
Psychometrics
Psychometrics - statistics & numerical data
Reproducibility of Results
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Personality trait inventories often perform poorly when their structure is evaluated with confirmatory factor analysis (CFA). The authors demonstrate poor CFA fit for several widely used personality measures with documented evidence of criterion-related validity but also show that some measures perform well from an exploratory factor analytic perspective. In light of these results, the authors suggest that the failure of these measures to fit CFA models is because of the inherent complexity of personality, issues related to its measurement, and issues related to the application and interpretation of CFA models. This leads to three recommendations for researchers interested in the structure and assessment of personality traits: (a) utilize and report on a range of factor analytic methods, (b) avoid global evaluations regarding the internal validity of multiscale personality measures based on model fit according to conventional CFA cutoffs, and (c) consider the substantive and practical implications of model modifications designed to improve fit.
ISSN:1088-8683
1532-7957
DOI:10.1177/1088868310361240