Exploratory Structural Equation Modeling: Practical Guidelines and Tutorial With a Convenient Online Tool for Mplus

Critics of positive psychology have questioned the validity of positive psychological assessment measures (PPAMs), which negatively affects the credibility and public perception of the discipline. Psychometric evaluations of PPAMs have shown that various instruments produce inconsistent factor structures between groups/contexts/times frames, that their predictive validity is questionable, and that popular PPAMs are culturally biased. Further, it would seem positive psychological researchers prioritize date-model-fit over measurement quality. To address these analytical challenges, more innovative and robust approaches toward the validation and evaluation of PPAMs are required to enhance the discipline's credibility and to advance positive psychological science. Exploratory Structural Equation Modeling (ESEM) has recently emerged as a promising alternative to overcome some of these challenges by incorporating the best elements from exploratory- and confirmatory factor analyses. ESEM is still a relatively novel approach, and estimating these models in statistical software packages can be complex and tedious. Therefore, the purpose of this paper is to provide novice researchers with a practical tutorial on how to estimate ESEM with a convenient online tool for Mplus. Specifically, we aim to demonstrate the use of ESEM through an illustrative example by using a popular positive psychological instrument: the Mental Health Continuum-SF. By using the MHC-SF as an example, we aim to provide (a) a brief overview of ESEM (and different ESEM models/approaches), (b) guidelines for novice researchers on how to estimate, compare, report, and interpret ESEM, and (c) a step-by-step tutorial on how to run ESEM analyses in Mplus with the De Beer and Van Zy ESEM syntax generator. The results of this study highlight the value of ESEM, over and above that of traditional confirmatory factor analytical approaches. The results also have practical implications for measuring mental health with the MHC-SF, illustrating that a bifactor ESEM Model fits the data significantly better than any other theoretical model.

Construct Validation of Self-Determination Theory in Second Language Scale: The Bifactor Exploratory Structural Equation Modeling Approach

The present study aimed to assess the construct validity of the Self-Determination Theory in Second Language Scale (SDT-L2; Alamer, 2021). The study involved 266 undergraduate students learning English as a second language (L2) in Saudi Arabia. The factorial structure of the SDT-L2 was examined using the advanced bifactor-Exploratory Structural Equation Modeling (ESEM) method. The scale provided adequate composite reliability and the bifactor ESEM provided unique details about the multidimensionality of the scale which accounted for the specific constructs (i.e., intrinsic, identified, introjected, and external regulations) and the general constructs (i.e., autonomous motivation and controlled motivation), and allowed for assessment of convergent and discriminant validity. Predictive validity was established by showing that autonomous motivation significantly predicted L2 performance, while controlled motivation did not. Overall, the study demonstrated the usefulness of the bifactor ESEM for construct validation purposes and the results showed that SDT-L2 is a valid scale to assess students’ L2 motivation based on SDT perspective.

A cross-cultural study of purposive “traits of action”: Measurement invariance of scales based on the action–trait theory of human motivation using exploratory structural equation modeling

The Action–Trait theory of human motivation posits that individual differences in predispositional traits of action may account for variance in contemporary purposeful human behavior. Prior research has supported the theory, psychometric properties of scales designed to assess the motive dimensions of the theory, and the utility of these scales to predict an array of behaviors, but this is the first study to evaluate the cross-linguistical invariance of the 15-factor theoretical model. This study evaluated translations of the English language 60-item Quick AIM in 5 samples – Croatian (N = 614), French (N = 246), German (N = 154), Polish (M = 314), and U.S. English (N = 490) – recruited from 4 countries (Croatia, Poland, Switzerland, and the U.S.). Exploratory structural equation modeling (ESEM) supported the theoretical model on which the traits of action are based and scrutinized the measurement invariance (configural, metric, scalar invariance) of the scale across the languages.

Investigating the Dimensionality of Early Numeracy Using the Bifactor Exploratory Structural Equation Modeling Framework

The few studies that have analyzed the factorial structure of early number skills have mainly used confirmatory factor analysis (CFA) and have yielded inconsistent results, since early numeracy is considered to be unidimensional, multidimensional or even underpinned by a general factor. Recently, the bifactor exploratory structural equation modeling (bifactor-ESEM)—which has been proposed as a way to overcome the shortcomings of both the CFA and the exploratory structural equation modeling (ESEM)—proved to be valuable to account for the multidimensionality and the hierarchical nature of several psychological constructs. The present study is the first to investigate the dimensionality of early number skills measurement through the application of the bifactor-ESEM framework. Using data from 644 prekindergarten and kindergarten children (4 to 6 years old), several competing models were contrasted: the one-factor CFA model; the independent cluster model (ICM-CFA); the exploratory structural equation modeling (ESEM); and their bifactor counterpart (bifactor-CFA and bifactor-ESEM, respectively). Results indicated acceptable fit indexes for the one-factor CFA and the ICM-CFA models and excellent fit for the others. Among these, the bifactor-ESEM with one general factor and three specific factors (Counting, Relations, Arithmetic) not only showed the best model fit, but also the best coherent factor loadings structure and full measurement invariance across gender. The bifactor-ESEM appears relevant to help disentangle and account for general and specific factors of early numerical ability. While early numerical ability appears to be mainly underpinned by a general factor whose exact nature still has to be determined, this study highlights that specific latent dimensions with substantive value also exist. Identifying these specific facets is important in order to increase quality of early numerical ability measurement, predictive validity, and for practical implications.

Is Burnout a Depressive Condition? A 14-Sample Meta-Analytic and Bifactor Analytic Study

There is no consensus on whether burnout constitutes a depressive condition or an original entity requiring specific medical and legal recognition. In this study, we examined burnout–depression overlap using 14 samples of individuals from various countries and occupational domains ( N = 12,417). Meta-analytically pooled disattenuated correlations indicated (a) that exhaustion—burnout’s core—is more closely associated with depressive symptoms than with the other putative dimensions of burnout (detachment and efficacy) and (b) that the exhaustion–depression association is problematically strong from a discriminant validity standpoint ( r = .80). The overlap of burnout’s core dimension with depression was further illuminated in 14 exploratory structural equation modeling bifactor analyses. Given their consistency across countries, languages, occupations, measures, and methods, our results offer a solid base of evidence in support of the view that burnout problematically overlaps with depression. We conclude by outlining avenues of research that depart from the use of the burnout construct.

Using Exploratory Structural Equation Modeling to Investigate the Construct Validity of the Critical Thinking Disposition Scale

One of the primary goals of higher education is to enhance students’ critical thinking skills as they work to complete their program of study. As such, it is for critical educators and academic program coordinators to have access to assessment tools that can provide accurate estimates of the cognitive and dispositional domains of higher-order thinking. Therefore, the current study was designed to provide evidence of the psychometric properties of the Critical Thinking Disposition Scale. Data were collected from 558 undergraduate and graduate students. Using exploratory structural equation modeling, we demonstrated that a 2-factor solution—consisting of critical openness and reflective skepticism dimensions—provided a good fit to the observed data. Additionally, our results showed critical openness and reflective skepticism scores were positively associated with conceptually related constructs (e.g., need for cognition and flexible thinking), demonstrating the convergent validity of the instrument. Our discussion concerns the potential utility of instrument for those interested in assessing critical thinking dispositions and avenues for future research.