Structural equation modeling is a comprehensive statistical methodology for evaluating hypothesized structural relationships among observed and latent variables. It integrates features of confirmatory factor analysis and path analysis, allowing researchers to test complex theoretical models representing direct and indirect effects.
Ontological type
Core Methods
Psychological Applications
Model Fit Evaluation
Standardized SEM Practice
1987 - 2007
Flexible Integrative SEM
2008 - 2014
Mature PLS-SEM Era
2015 - 2024
Standardized SEM Practice era
Kenneth A. Bollen [1] is associated with the University of Iowa [3] and the University of North Carolina at Chapel Hill [4] during this era, and his seminal works include Structural Equations with Latent Variables [7] and Testing Structural Equation Models [8]. These papers introduced latent-variable modeling and formal testing of SEM, laying groundwork for model evaluation and invariance testing that became standard in the era. Peter M. Bentler [2] is linked to the University of California, Los Angeles [5] and the University of California, Berkeley [6] during this era, with works including Comparative fit indexes in structural models [9], Practical Issues in Structural Modeling [10], and Comparative Fit Indices in Structural Models [11]. These contributions advanced standardized model evaluation and multigroup comparison, reinforcing fit-index practice and practical estimation guidance.
Flexible Integrative SEM era
Marko Sarstedt [1] was affiliated with Ludwig-Maximilians-Universität München [3] and the University of Newcastle Australia [4] during the Flexible Integrative SEM era. His key contributions in this era include critical assessments and methodological guidance through papers such as 'An assessment of the use of partial least squares structural equation modeling in marketing research' [6], 'Goodness-of-fit indices for partial least squares path modeling' [7], and 'A critical look at the use of PLS-SEM in MIS Quarterly' [8], which together advanced appropriate application, interpretation of fit indices, and reflexivity about PLS-SEM in a flexible measurement context. Christian M. Ringle [2] is associated with Universität Hamburg [5] and the University of Newcastle Australia [4] during this era. His contributions include papers such as 'An assessment of the use of partial least squares structural equation modeling in marketing research' [6] and 'A critical look at the use of PLS-SEM in MIS Quarterly' [8], which helped anchor critical discourse across marketing and MIS contexts and influenced how researchers evaluate PLS-SEM in flexible integrative SEM.
Mature PLS-SEM Era era
Marko Sarstedt [1] is associated with Ludwig-Maximilians-Universität München [3] and University of Newcastle Australia [4] in the Mature PLS-SEM Era. His key contributions include recommendations on when to use and how to report the results of PLS-SEM [7], guidance on how to specify, estimate, and validate higher-order constructs in PLS-SEM [8], and testing measurement invariance of composites using partial least squares [9], which advanced rigorous practice, transparent reporting, and predictive validity in this era. Christian M. Ringle [2] is affiliated with James Cook University [5] and Universität Hamburg [6] in this era. Ringle [2] co-authored these works [7][8][9], which promoted rigorous reporting, measurement invariance testing, and higher-order construct handling, advancing standards in predictive modeling and cross-validation in this era.