Structural equation modeling: strengths, limitations, and misconceptions.

By Andrew Tomarken, N. Waller. Annual Review of Clinical Psychology, 2005

906 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/236f151ba111c689c58b2ad400f50199c7e08e29

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Best-Practice Recommendations for Defining, Identifying, and Handling Outliers (2013, methodology): “…standpoint, our recommendations are also based on the availability of these techniques in widely used software packages for regression (Cohen et al., 2003), SEM (Byrne, 2001; Tomarken & Waller, 2005; Zhang & Yuan, 2012), and multilevel modeling (Raudenbush, Bryk, Cheong, Congdon, & Du Toit, 2004).”
The Questionnaire for Eudaimonic Well-Being: Psychometric properties, demographic comparisons, and evidence of validity (2010, neutral): “The comparative fit index (CFI) and the non-normed fit index (NNFI) should be 0.95 or greater, and the root mean square error of approximation (RMSEA) and the standardized root mean square residual (SRMR) should be 0.06 or below (Hancock & Freeman, 2001; Tomarken & Waller, 2005).”
Employment, Sense of Coherence, and Identity Formation (2008, background): “…cross-sectional research, where directionality and sequentiality cannot be empirically tested, it is essential to demonstrate that the theoretical model retained as described in Model B provides a better fit than alternative models positing different directions of effects (Tomarken & Waller, 2005).”
Genes and Ideologies (2008, methodology): “As Tomarken and Waller 2005 (56) note of the use of SEM in twin studies, “sophisticated statistical procedures cannot rescue a poorly designed study.””
Multivariate Meta-Analysis as Structural Equation Models (2013, positive): “SEM is now a standard statistical model to fit various models in the social and behavioral sciences (Bollen, 2002; MacCallum & Austin, 2000; Tomarken & Waller, 2005).”
A Longitudinal Examination of Latino Adolescents' Ethnic Identity, Coping With Discrimination, and Self-Esteem (2008, background): “A particular strength of our study is the ability to test alternative longitudinal models (cf. Tomarken & Waller, 2003, 2005).”
Exploratory structural equation modeling: an integration of the best features of exploratory and confirmatory factor analysis. (2014, background): “Indeed, Tomarken & Waller (2005) have highlighted the importance of CFA/SEM in clinical psychology, noting the large number of publications that indicate it has become the most commonly used multivariate technique.”
The effects of service quality, image, and customer satisfaction on customer complaints and loyalty in high-speed rail service in Turkey: a proposal of the structural equation model (2017, methodology): “Mardia test statistic can be used to validate this assumption (Mardia 1970; Bollen 1989; Andrew, Waller, and Waller 2004).”
Factors Influencing Preservice Teachers' Intention to Use Technology: TPACK, Teacher Self-efficacy, and Technology Acceptance Model (2018, background): “SEM can analyze the integrated relationship among all variables in this study, and to estimate the relations among the variables that have been corrected for biases attributable to random error and construct-irrelevant variance (Bollen, 1989; Tomarken & Waller, 2005).”
Structure and flexibility: Investigating the relation between the structure of the mental lexicon, fluid intelligence, and creative achievement. (2016, background): “SEM cannot determine the exact nature of this mediating effect, as it only indicates the weight of the relation linking the latent variable and the dependent variable (MacCallum & Austin, 2000; MacKinnon, Fairchild, & Fritz, 2007; Tomarken & Waller, 2005).”
Beyond pleasure: Exploring the eudaimonic entertainment experience. (2012, background): “This dimension of eudaimonic entertainment is deduced from what Waterman (1993) calls ‘‘living in accordance with one’s central values.”
Using Group-Based Trajectory and Growth Mixture Modeling to Identify Classes of Change Trajectories (2016, methodology): “Of course, correct model specification is important for all modeling techniques (Tomarken & Waller, 2005), but idiosyncratic data patterns and groups are particularly vulnerable to reification in GBTM and LGMM because these procedures are data-driven (Bauer & Curran, 2003b).”