To account for the constructivist character of the artifact, the composite has been recently suggested for its operationalization in SEM (Henseler, 2017). However, for artifacts the idea of measurement is unrewarding as they are rather constructed to fulfill a certain purpose. It assumes that each observable indicator is a manifestation of the underlying concept that is regarded as their common cause (Reichenbach, 1956), and therefore fully explains the covariation among its indicators. Typically, the common factor model is used to operationalize behavioral concepts, because it is well matched with the general understanding of measurement (Sobel, 1997). Table Table1 1 displays further examples of disciplines investigating behavioral concepts and artifacts. For example Psychiatry: on the one hand it examines clinical relevant behavior to understand mental disorder, but on the other hand it also aims at developing mental disorder treatments (Kirmayer and Crafa, 2014). Although the common factor model has demonstrated its usefulness for concepts of behavioral research such as traits and attitudes, the limitation of SEM to the factor model is unfortunate because many disciplines besides and even within social and behavioral sciences do not exclusively deal with behavioral concepts, but also with design concepts (so-called artifacts) and their interplay with behavioral concepts. Over the last decades, the operationalization of the theoretical concept and the common factor has become more and more conflated such that hardly any distinction is made between the terms (Rigdon, 2012). Additionally, beyond the realm of behavioral and social sciences, researchers have acknowledged the capabilities of SEM, such as in construction research (Xiong et al., 2015) or neurosciences (McIntosh and Gonzalez-Lima, 1994). In particular, in the behavioral and social sciences, SEM enjoys wide popularity, e.g., in marketing (Bagozzi and Yi, 1988 Steenkamp and Baumgartner, 2000), psychology (MacCallum and Austin, 2000), communication science (Holbert and Stephenson, 2002), operations management (Shah and Goldstein, 2006), and information systems (Gefen et al., 2011),-to name a few. Researchers across many streams of science appreciate SEM's versatility as well as its ability to test common factor models. Consequently, SEM is able to deal with categorical (Muthén, 1984) as well as longitudinal data (Little, 2013) and can be used to model non-linear relationships between the constructs (Klein and Moosbrugger, 2000). Over time, the initial model has been continuously improved upon to account for more complex theories. Apart from the original maximum likelihood estimator, robust versions and a number of alternative estimators were also introduced to encounter violations of the original assumptions in empirical work, such as the asymptotic distribution free (Browne, 1984) or the two-stage least squares (2SLS) estimator (Bollen, 2001). Since SEM allows for statistical testing of the estimated parameters and even entire models, it is an outstanding tool for confirmatory purposes such as for assessing construct validity (Markus and Borsboom, 2013) or for establishing measurement invariance (Van de Schoot et al., 2012). It is capable of expressing theoretical concepts by means of multiple observable indicators to connect them via the structural model as well as to account for measurement error. Structural equation modeling with latent variables (SEM) comprises confirmatory factor analysis (CFA) and path analysis, thus combining methodological developments from different disciplines such as psychology, sociology, and economics, while covering a broad variety of traditional multivariate statistical procedures (Bollen, 1989 Muthén, 2002). A Monte Carlo simulation examines the efficacy of CCA, and demonstrates that CCA is able to detect various forms of model misspecification. Model assessment mainly relies on the Bollen-Stine bootstrap to assess the discrepancy between the empirical and the estimated model-implied indicator covariance matrix. For the estimation of the model, several estimators are available in particular Kettenring's extensions of canonical correlation analysis provide consistent estimates. Researchers must ensure theoretical identification of their specified model. Composite models are specified such that they consist of a set of interrelated composites, all of which emerge as linear combinations of observable variables. CCA entails the same steps as confirmatory factor analysis: model specification, model identification, model estimation, and model assessment. It facilitates the operationalization and assessment of design concepts, so-called artifacts. This article introduces confirmatory composite analysis (CCA) as a structural equation modeling technique that aims at testing composite models.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |