Exploring social and personal relationships: The issue of measurement invariance of non-independent observations

摘要: In social psychology, some research questions address a comparison of individuals belonging to different or relational contexts. As measurement invariance literature has indicated, before comparing two more groups (gender, cultures, and relationship types), the question whether construct used for is invariant must be verified. Measurement helps assure validity equivalence across groups. However, when non-independent data are (the same individual provides his her standard multigroup analyses testing not accurate. The current study presents modified correlated uniqueness model that may applied in these specific cases. an example, we analyzed Intimate Disclosure scale Conflict mother–child, father–child, romantic relationships young adults. Results indicate partial invariance: only configural invariance, factor loading covariance were found. consequences then discussed. Copyright © 2014 John Wiley & Sons, Ltd.