Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality

Factor analysis and nomological network analysis are commonly used as complementary procedures in the investigation of the dimensionality of constructs (e.g., self-esteem, job satisfaction). Although it has been demonstrated that factor analyses are often biased toward a two-dimensional solution for...

Full description

Bibliographic Details
Main Authors: Seng Kam, C., Meyer, John
Format: Journal Article
Published: 2015
Online Access:http://hdl.handle.net/20.500.11937/10878
_version_ 1848747654739132416
author Seng Kam, C.
Meyer, John
author_facet Seng Kam, C.
Meyer, John
author_sort Seng Kam, C.
building Curtin Institutional Repository
collection Online Access
description Factor analysis and nomological network analysis are commonly used as complementary procedures in the investigation of the dimensionality of constructs (e.g., self-esteem, job satisfaction). Although it has been demonstrated that factor analyses are often biased toward a two-dimensional solution for measures including regular- and reverse-keyed items, less attention has been paid to the implications for nomological network analyses. We propose, and demonstrate empirically in two studies, that item keying is confounded with item valence (i.e., favorability of item content), and that item valence can bias the results of both factor analysis and nomological network analysis toward a two-dimensional interpretation. We also demonstrate that the valence effect is related to, but distinguishable from, social desirability response bias. We caution that the practice of excluding reverse-keyed items to achieve unidimensionality can lead to distortion in correlations among constructs, and we offer alternative remedies to the valence problem.
first_indexed 2025-11-14T06:52:35Z
format Journal Article
id curtin-20.500.11937-10878
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:52:35Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-108782017-09-13T14:56:21Z Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality Seng Kam, C. Meyer, John Factor analysis and nomological network analysis are commonly used as complementary procedures in the investigation of the dimensionality of constructs (e.g., self-esteem, job satisfaction). Although it has been demonstrated that factor analyses are often biased toward a two-dimensional solution for measures including regular- and reverse-keyed items, less attention has been paid to the implications for nomological network analyses. We propose, and demonstrate empirically in two studies, that item keying is confounded with item valence (i.e., favorability of item content), and that item valence can bias the results of both factor analysis and nomological network analysis toward a two-dimensional interpretation. We also demonstrate that the valence effect is related to, but distinguishable from, social desirability response bias. We caution that the practice of excluding reverse-keyed items to achieve unidimensionality can lead to distortion in correlations among constructs, and we offer alternative remedies to the valence problem. 2015 Journal Article http://hdl.handle.net/20.500.11937/10878 10.1080/00273171.2015.1022640 restricted
spellingShingle Seng Kam, C.
Meyer, John
Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title_full Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title_fullStr Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title_full_unstemmed Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title_short Implications of Item Keying and Item Valence for the Investigation of Construct Dimensionality
title_sort implications of item keying and item valence for the investigation of construct dimensionality
url http://hdl.handle.net/20.500.11937/10878