Abstract
Confirmatory composite analysis (CCA) is a structural equation modeling (SEM) technique that specifies and assesses composite models. In a composite model, the construct emerges as a linear combination of observed variables. CCA was invented by Jörg Henseler and Theo K. Dijkstra in 2014, was subsequently fully elaborated by Schuberth et al. (2018), and was then introduced into business research by Henseler and Schuberth (2020b). Inspired by Hair et al. (2020), a recent article in the International Journal of Information Management (Motamarri et al., 2020) used the same term ‘confirmatory composite analysis’ as a technique for confirming measurement quality in partial least squares structural equation modeling (PLS-SEM) specifically. However, the original CCA (Henseler et al., 2014; Schuberth et al., 2018) and the Hair et al. (2020) technique are very different methods, used for entirely different purposes and objectives. So as to not confuse researchers, we advocate that the later-published Hair et al. (2020) method of confirming measurement quality in PLS-SEM be termed ‘method of confirming measurement quality’ (MCMQ) or ‘partial least squares confirmatory composite analysis’ (PLS-CCA). We write this research note to clarify the differences between CCA and PLS-CCA.
Highlights
Confirmatory composite analysis (CCA) as sketched by Henseler et al (2014) and elaborated by Schuberth, Henseler, & Dijkstra (2018) is a novel approach to structural equation modeling (SEM)
The evidence regarding the efficacy of partial least squares confirmatory composite analysis’ (PLS-CCA)’s evaluation steps has been questioned in the literature (McIntosh, Edwards, & Antonakis, 2014; Ronkko, McIntosh, Antonakis & Edwards, 2016; Schuberth, 2021b). This is due to the fact that most of the metrics employed to validate reflective partial least squares structural equation modeling (PLS-SEM) measurement models such as indicator reliability, Cronbach’s alpha, composite reli ability, average variance extracted, and the heterotrait-monotrait ratio of correlations have been derived under the common factor model, i.e., a reflective measurement model known from SEM comprising a latent variable
While CCA is not tied to PLS, the latter can be used as an estimator for CCA in some circumstances
Summary
Confirmatory composite analysis (CCA) as sketched by Henseler et al (2014) and elaborated by Schuberth, Henseler, & Dijkstra (2018) is a novel approach to structural equation modeling (SEM). The authors apply consistent partial least squares (PLSc, Dijkstra & Henseler, 2015a, 2015b) in combination with existing, well-known evaluation steps from partial least squares structural equation modeling (PLS-SEM, Hair et al, 2011). What Hair et al (2020) describe as ‘confirmatory composite analysis’ summarizes the many long-standing approaches and techniques used to evaluate the quality of PLS-SEM measurement models. These models comprise formative or reflective PLS-SEM measurement models to operationalize concepts such as attitudes and beliefs, which cannot be directly observed but which are typically assumed to exist in nature.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
