Premium
A closer look at the measurement of dispositional reasoning: Dimensionality and invariance across assessor groups
Author(s) -
De Kock François S.,
Lievens Filip,
Born Marise Ph.
Publication year - 2017
Publication title -
international journal of selection and assessment
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.812
H-Index - 61
eISSN - 1468-2389
pISSN - 0965-075X
DOI - 10.1111/ijsa.12176
Subject(s) - measurement invariance , psychology , construct (python library) , curse of dimensionality , metric (unit) , social psychology , cognitive psychology , confirmatory factor analysis , artificial intelligence , structural equation modeling , statistics , computer science , mathematics , operations management , economics , programming language
Despite the growing interest in dispositional reasoning as a construct and determinant of good raters (‘good judges’), its measurement still requires attention. We address two measurement issues in the present study. First, this study tests a hierarchical model as a more parsimonious account for dispositional reasoning than component‐ or general‐factor models that were examined in earlier studies. So, this provides a more comprehensive test of the different measurement models underlying dispositional reasoning data. Second, we assess the measurement invariance of dispositional reasoning measure scores across two different populations of assessors that are often trained and used in workplace assessments, namely psychology students ( N = 161) and managers ( N = 160). Results showed that dispositional reasoning is well represented as componential in nature, with a higher‐order construct underlying three lower‐order components. A comparison of managers and psychology students through measurement invariance analysis showed relatively similar factor structures underlying dispositional reasoning scores across these groups, but metric invariance could be only partially established.