Exploratory structural equation modeling: a streamlined step by step approach using the R Project software

Allen and Meyer's(1990) 3-component model of organizational commitment(OC) was investigated using exploratory structural equation modeling(ESEM) with samples of full-time social workers at social welfare organizations in South Korea. Confirmatory factor analysis(CFA) has been at the heart of testing factor structure of the 3-component model in organizational commitment research wherein each scale of the affective, continuance, and normative commitment is reported to measure conceptually and empirically separable construct. The present study applied ESEM, specifically ‘intra-scale’ and ‘inter-scale’ ESEM, to scrutinize factor structure of the 3-component scales. ESEM methodology uses exploratory approach in that all cross-loadings are estimated between each measure and factors, with uniqueness correlated according to the researcher's hypotheses as in CFA. In this respect, ESEM can be viewed as an open approach to item analysis distinguished from the conventional (closed) approach, such as EFA and CFA. This study provided detailed assessment of the 3-component model through comparisons of factor structures estimated by EFA, CFA and ‘intra’ ESEM, followed by the ‘inter’ ESEM conducted on all other variables(assumed to be similar constructs with or antecedents of OC). As a result, the ‘intra-scale’ ESEM showed a substantially better fit and yielded more discriminated factors(less correlated) than did EFA and CFA that are models for planned scale. The ‘inter-scale’ ESEM revealed how seriously method effect can distort an original factor structure in empirical data measured together with multiple scales of other constructs. Using ESEM has advantages of estimating common factor structures, controlling for common method effect that are typically included in measures in applied research. Also, it allows for much more possibilities that each item can measure multiple constructs so as to reveal more realistic factor structures. Taken together, the present results suggest a need to conceptualize and validate a new scale for organizational commitment reflecting Korean culture.

Objectives: Developed countries are becoming more multi-ethnic, with consequent problems of maintaining invariance of health questionnaires. We aimed to explore commonalities in the structure of the Strengths and Difficulties Questionnaire (SDQ) completed for young children in a multi-ethnic English cohort while examining potential method effects and misfitting items. The secondary aim was to demonstrate the usefulness of bifactor modelling and exploratory structural equation modelling (ESEM) for kinanthropological research. Methods: We used SDQ data from 3,290 children enrolled in the Born in Bradford cohort, completed by parents (usually the mother) at child age 3 and 4 and teachers at age 5. The factor structure for 11 potential configurations was assessed in each age group using confirmatory factor analysis. ESEM was used to assess misfitting items under the best fitting configuration. Results: The best fitting configuration was a bifactor model of the 2 broader scales and a methods factor, using the 20 difficulties items. Generally, factor loadings increased between age 3 and age 5. Several items contributed to misfit. Conclusions: There was less support for the robustness and hypothesised structure of the SDQ in this sample. Bifactor scores that account for measurement error could be useful if carefully applied in epidemiological and kinanthropological studies in multi-ethnic and/or younger age samples.

This study offers methodological synergy in the examination of factorial structure in second language (L2) research. It illustrates the effectiveness and flexibility of the recently developed exploratory structural equation modeling (ESEM) method, which integrates the advantages of exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) into one complete measurement model. Two sets of data were collected using the L2 Passion Scale, which measures a dualistic model of passion. Study 1 participants were 220 L2 students. A comparison was made between the CFA and the ESEM models. The results demonstrated the superiority of the ESEM method relative to CFA in terms of better goodness-of-fit indices and realistic correlated factors. These results were replicated in another sample of 272 L2 students, providing support for the predictive validity using a structural ESEM model. Guidelines are provided and Mplus syntax files (codes) are included to help analysts apply the methods. We also make the data available publicly. Overall, this research demonstrated the usefulness of ESEM for examining the construct, discriminant, and convergent validity of L2 scales over CFA.

The factorial validity of the Cornell Critical Thinking Tests: A multi-analytic approach

Teacher-child relationships in early childhood are a fundamental prerequisite for children's social, emotional, and academic development. The Student-Teacher Relationship Scale (STRS) is one of the most widely accepted and used instruments that evaluate the quality of teacher-child relationships. STRS is a 28-item questionnaire that assess three relational dimensions, Closeness, Conflict, and Dependency. The relevant literature has shown a pattern regarding the difficulty to support the STRS factor structure with CFA, while it is well-documented with EFA. Recently, a new statistical technique was proposed to combine the best of the CFA and EFA namely, the Exploratory Structural Equation Modeling (ESEM). The purpose of this study was (a) to examine the factor structure of the STRS in a Greek national sample. Toward this end, the ESEM framework was applied in order to overcome the limitations of EFA and CFA, (b) to confirm previous findings about the cultural influence in teacher-child relationship patterns, and (c) to examine the invariance of STRS across gender and age. Early educators from a representative Greek sample size of 535 child care and kindergarten centers completed the STRS for 4,158 children. CFA as well as ESEM procedures were implemented. Results showed that ESEM provided better fit to the data than CFA in both groups, supporting the argument that CFA is an overly restrictive approach in comparison to ESEM for the study of STRS. All primary loadings were statistically significant and were associated with their respective latent factors. Contrary to the existing literature conducted in USA and northern Europe, the association between Closeness and Dependency yielded a positive correlation. This finding is in line with previous studies conducted in Greece and confirm the existence of cultural differences in teacher-child relationships. In addition, findings supported the configural, metric, scalar, and variance/covariance equivalence of the STRS between males and females and between preschoolers (3–5 years) and early primary years (5–7 years). Latent factor means comparisons showed that females seem to have a warmer and more dependent relationship with their teachers and are less conflictual in comparison to males.

The Depression Anxiety and Stress Scales-21 (DASS-21) involves a simple structure first-order three-factor oblique model, with factors for depression, anxiety, and stress. Recently, concerns have been raised over the value of using confirmatory factor analysis (CFA) for studying the factor structure of scales in general. However, such concerns can be circumvented using exploratory structural equation modeling (ESEM). Consequently, the present study used CFA and ESEM with target rotation to examine the factor structure of the DASS-21 among an adult community. It compared first-order CFA, ESEM with target rotation, bi-factor CFA (BCFA), and bi-factor BESEM with target rotation models with group/specific factors for depression, anxiety, and stress. A total of 738 adults (males = 374, and females = 364; M = 25.29 years; SD = 7.61 years) completed the DASS-21. While all models examined showed good global fit values, one or more of the group/specific factors in the BCFA, ESEM with target rotation and BESEM with target rotation models were poorly defined. As the first-order CFA model was most parsimonious, with well-defined factors that were also supported in terms of their reliabilities and validities, this model was selected as the preferred DASS-21 model. The implications of the findings for use and revision of the DASS-21 are discussed.

Revised reinforcement sensitivity theory (r-RST) of personality is a major neuropsychological theory of motivation, emotion and personality. This paper presents the results of a study examining: (1) the factor structure of the Reinforcement Sensitivity Theory of Personality Questionnaire (RST-PQ) using confirmatory factor analysis (CFA) and exploratory structural equation modeling (ESEM); and (2) the relationships of the r-RST constructs in the RST-PQ with attention deficit hyperactivity disorder (ADHD) symptom groups of inattention (IA) and hyperactivity/impulsivity (HI). A total of 572 (Sample 1) and 309 (Sample 2) adults completed the RST-PQ. Participants in Sample 2 also completed a questionnaire measuring ADHD symptoms. Results revealed more support for the ESEM model with six factors than the CFA model. For both the ESEM and CFA models, both IA and HI symptom groups were associated positively with the RST-PQ constructs of behavioral inhibition system (BIS) and behavioral approach system (BAS) Impulsivity, with IA also associated negatively with the BAS-Goal-Drive Persistence. The theoretical implications of these findings for understanding the factor structure of the RST-PQ, and for ADHD (IA and HI) in terms of r-RST, are discussed.

Investigators frequently use the Perceived Stress Scale (PSS-10) to evaluate the extent to which external demands exceed perceived capacity to manage pressure. Analysts utilizing confirmatory factor analysis (CFA) assert that a bifactor model best fits PSS-10 data, though support exists for a two-factor conceptualisation. Since theorists contend that CFA has limitations, this paper assessed whether exploratory structural equation modelling (ESEM) provided a superior factorial solution. Accordingly, this research assessed the adequacy of two-factor vs. bifactor models using CFA and ESEM. Additionally, analyses tested convergent validity, invariance, and predictive validity in relation to well-being outcomes (Life Satisfaction and Somatic Complaints). In Study 1, 1556 (802 males, 754 females) UK-based participants completed the PSS-10 at time points six months apart. In Study 2, 1630 (838 males, 784 females, eight non-binary) UK-based participants completed the PSS-10 alongside measures of Life Satisfaction and Somatic Complaints. Study 1, using latent modelling, found that the two-factor ESEM model (containing Distress and Counter-Stress factors) produced superior fit (vs. CFA and bifactor solutions). In Study 2, structural equation modelling revealed acceptable predictive validity for the two-factor solution; Distress predicted Somatic Complaints and Counter-Stress predicted Life Satisfaction. Gender (Study 1 and 2) and time (Study 1) demonstrated measurement invariance. Latent means across studies indicated that females (vs. males) scored higher on Distress. Overall, ESEM estimated the PSS-10 more accurately. Findings supported the utility of Distress and Counter-Stress factors for predicting well-being indicators. Future research is necessary to consider this distinction in relation to allied health outcomes.

Validation of the Malay version of the recovery-stress questionnaire for athletes: Application of confirmatory factor analysis and exploratory structural equation modeling

Identity is a powerful concept that influences behavior and health. For over thirty years, researchers in sport psychology have been using the Athletic Identity Measurement Scale (AIMS) as a research instrument providing insights into the relationships between athletic identity and health variables. While musician identity is recognized as an important factor to be investigated in relation to occupational health, there are no known robust instruments like the AIMS in music psychology research. The current study aimed to adapt and validate the athletic identity measurement scale for use with musicians. The AIMS history includes episodes of modifications for performance enhancement of the instrument that resulted in five different models. The validation process includes evaluating the psychometrical properties across all five models. The sample included student musicians and non-student musicians (N = 1040). The traditional confirmatory factor analysis (CFA) and the maximum likelihood (ML) estimation method were used. The exploratory structural equation modeling (ESEM) and robust weighted least squares (WLS) was utilized to explore a new method of estimation that was known to resolve issues consistent with the CFA and ML method. The goodness-of-fit indices of CFA and ESEM were compared. The results showed that the MIMS is a reliable and valid instrument for use with musicians. The factor structure and the goodness-of fit-indices were discussed across all the models of MIMS.

This survey study aimed to contribute to the extensive debate on the dimensionality of the Posttraumatic Stress Disorder Checklist for the DSM-5 (PCL-5) questionnaire by examining the psychometric properties and construct validity of its Hungarian version and relying on the inspection of a conceptual network of related variables, that is, perceived stress, hostility, and resilience. Confirmatory factor analysis (CFA), exploratory structural equation modelling (ESEM) and path analysis were applied on data collected from 177 paramedics and 66 professionals from the social field (58.4% male; Mage=43.5±9.96years). Despite the acceptable fit indices gained with CFA when testing the original four-factor DSM-5 model of PCL-5, strong associations (r=0.69-0.90) between subscales were found. Thus, ESEM was applied and as a result a new, three-factor version of the DSM-5 model of PCL-5 was proposed due to significant crossloadings that was theoretically also supported. The Reexperiencing and Avoidance subscales were merged and named Difficulty with Assimilation of Experience (DAE). In the path analysis only two of the tested associations were not significant using the new factor structure, in which stress fully mediated the relationship between resilience and DAE, and resilience and Hyperarousal. Overall, the hypothesised pathways between variables fit the collected data well. (weighted least squares mean-and variance-adjusted χ2=503.750 (df=270), comparative fit index=0.948, Tucker-Lewis index=0.939, root mean square error of approximation (90% confidence interval)=0.064 (0.055-0.073), weighted root mean square residual=1.024). Our analysis of the Hungarian version of PCL-5 contributes to the testing of a DSM-5-based questionnaire measuring posttraumatic stress disorder symptomology.

With its emphasis on practical and conceptual aspects, rather than mathematics or formulas, this accessible book has established itself as the go-to resource on confirmatory factor analysis (CFA). Detailed, worked-through examples drawn from psychology, management, and sociology studies illustrate the procedures, pitfalls, and extensions of CFA methodology. The text shows how to formulate, program, and interpret CFA models using popular latent variable software packages (LISREL, Mplus, EQS, SAS/CALIS); understand the similarities and differences between CFA and exploratory factor analysis (EFA); and report results from a CFA study. It is filled with useful advice and tables that outline the procedures. The companion website offers data and program syntax files for most of the research examples, as well as links to CFA-related resources. New to This Edition *Updated throughout to incorporate important developments in latent variable modeling. *Chapter on Bayesian CFA and multilevel measurement models. *Addresses new topics (with examples): exploratory structural equation modeling, bifactor analysis, measurement invariance evaluation with categorical indicators, and a new method for scaling latent variables. *Utilizes the latest versions of major latent variable software packages--

BackgroundHereditary hemorrhagic telangiectasia (HHT) disease is a rare genetic disorder with symptoms and complications that can significantly affect patients’ daily lives. To date, no scale has been validated to assess the specific symptoms of this disease on the quality of life (QOL) of HHT patients. This makes it difficult for clinicians to accurately measure the quality of life of patients with HHT. The present study aims to develop and validate a QOL measurement tool specific to HHT disease: the QOL questionnaire in HHT (QoL-HHT).MethodsA quantitative, non-interventional, multi-center study involving HHT patients in twenty French HHT expert centers was conducted. A calibration sample of 415 HHT patients and a validation sample of 228 HHT patients voluntarily participated in the study. Data were analyzed using exploratory factor analysis (EFA), confirmatory factor analysis (CFA), Exploratory Structural Equation Modeling (ESEM) analyses, reliability analyses, and correlational analyses.ResultsThe EFA, CFA and ESEM results allowed us to provide evidence of the factorial structure of a questionnaire composed of 24 items measuring 6 domains of QOL: Physical limitations, social relationships, concern about bleeding, relationship with the medical profession, experience of symptoms, and concern about the evolution of the disease. Cronbach’s alpha coefficients (> 0.70) demonstrated reliable internal consistency of all the QoL-HHT scores (dimensions). The results of the test–retest provided further evidence of the reliability of the QOL-HHT scores over time. Correlational analyses provided evidence for the convergent validity of the QoL-HHT scores.ConclusionsWe developed a simple and quick self-assessment tool to measure quality of life specific to HHT disease. This study demonstrated reliability and validity of our QoL-HHT scores. It is a very promising tool to evaluate the impact of HHT disease on all aspects of the quality of life of HHT patients in order to offer them individualized medico-psycho-social support.Trial registration: ClinicalTrials, NCT03695874. Registered 04 October 2018, https://www.clinicaltrials.gov/ct2/show/NCT03695874

ObjectiveDevelopment and testing of a comprehensive and social and culturally inclusive child-report measure of resilience factors supporting positive outcomes in the face of adversity.DesignThe measure is based on a socioecological...

ABSTRACTThe multi-dimensionality of Physical Self-Perception Profile (PSPP) has been acknowledged by the use of correlated-factor model and second-order model. In this study, the authors critically endorse the bifactor model, as a substitute to address the multi-dimensionality of PSPP. To cross-validate the models, analyses are conducted first in exploratory structural equation modeling (ESEM) framework with a randomly selected subsample and then in confirmatory factor analysis (CFA) framework with a second subsample. Results from both ESEM and CFA analyses suggest that bifactor model is the best-fitted model. A general physical self-esteem factor and four domain specific factors are identified with the bifactor model. Coefficient omega hierarchical of the general factor is .86. The of the specific factors are .19, .20, .59, and .29, respectively. Gender difference at both general factor level and domain specific factor level is examined within the bifactor model. Discussions of the use and limitations of bifactor model as well as ESEM are provided.