Skip to main content

Research Repository

Advanced Search

Are personality trait items reliably more or less 'difficult'? Mokken scaling of the NEO-FFI

Watson, Roger; Deary, Ian; Austin, Elizabeth

Authors

Ian Deary

Elizabeth Austin



Abstract

The psychometric properties of self-report scales, such as the NEO-Five Factor Inventory (NEO-FFI), are examined using a range of statistical methods such as factor analysis. These methods establish, among other things, whether items in a scale covary and whether this indicates latent traits to the construct under investigation. The present study was designed to apply an additional analytical tool to the NEO-FFI, to investigate whether or not the items in its scales form hierarchies. Mokken scaling is designed to search multivariate data for ordinal, unidimensional and hierarchical scales. It was applied in the present study using the Mokken Scaling Procedure software. NEO-FFI data from 1028 subjects were entered into the Mokken Scaling Procedure. Following checks for scalability, monotonicity and double monotonicity one scale was obtained from the neuroticism dimension of the NEO-FFI. The data indicate that some items related to neuroticism in the NEO-FFI form a reliable hierarchy. There may be practical applications of hierarchical scales, with items having different level of 'difficulty' in personality research. © 2007 Elsevier Ltd. All rights reserved.

Citation

Watson, R., Deary, I., & Austin, E. (2007). Are personality trait items reliably more or less 'difficult'? Mokken scaling of the NEO-FFI. Personality and individual differences, 43(6), 1460-1469. https://doi.org/10.1016/j.paid.2007.04.023

Journal Article Type Article
Acceptance Date Apr 16, 2007
Online Publication Date Jun 5, 2007
Publication Date 2007-10
Journal PERSONALITY AND INDIVIDUAL DIFFERENCES
Print ISSN 0191-8869
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 43
Issue 6
Pages 1460-1469
DOI https://doi.org/10.1016/j.paid.2007.04.023
Keywords Personality; NEO-FFI; Mokken scaling; Factor analysis; Guttman scaling; Latent traits; Psychometrics; Item-response theory
Public URL https://hull-repository.worktribe.com/output/423750
Publisher URL https://www.sciencedirect.com/science/article/pii/S0191886907001547?via%3Dihub