Explaining general and specific factors in longitudinal, multimethod, and bifactor models: Some caveats and recommendations.

Koch, Tobias; Holtmann, Jana; Bohn, Johannes; Eid, Michael

doi:10.1037/met0000146

Cited by 52 publications

(47 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To investigate this, bifactor models can be used that incorporate both a general factor and domain-specific group factors (e.g., Lahey et al, 2017). Although it has been pointed out that bifactor models can become complex and very hard to interpret (Eid et al, in press; Koch et al, in press), their use in structural research of mental disorders is an interesting topic for further investigation.…”

Section: Discussionmentioning

confidence: 99%

The cross-national structure of mental disorders: results from the World Mental Health Surveys

et al. 2017

View full text Add to dashboard Cite

Background The patterns of comorbidity among mental disorders have led researchers to model the underlying structure of psychopathology. While studies have suggested a structure including internalizing and externalizing disorders, less is known with regard to the cross-national stability of this model. Moreover, little data is available on the placement of eating disorders, bipolar disorder and psychotic experiences in this structure. Methods We evaluated the structure of mental disorders with data from the World Health Organization Composite International Diagnostic Interview, including 15 lifetime mental disorders and six psychotic experiences. Respondents (n=5,478–15,499) were included from 10 high, middle and lower-middle income countries across the world aged 18 years or older. Confirmatory Factor Analyses (CFA) were used to evaluate and compare the fit of different factor structures to the lifetime disorder data. measurement invariance was evaluated with multigroup CFA (MG-CFA). Results A second-order model with internalizing and externalizing factors and fear and distress subfactors best described the structure of common mental disorders. MG-CFA showed that this model was stable across countries. Of the uncommon disorders, bipolar disorder and eating disorder were best grouped with the internalizing factor, and psychotic experiences with a separate factor. Conclusions These results indicate that cross-national patterns of lifetime common mental-disorder comorbidity can be explained with a second-order underlying structure that is stable across countries and can be extended to also cover less common mental disorders.

show abstract

Section: Discussionmentioning

confidence: 99%

The cross-national structure of mental disorders: results from the World Mental Health Surveys

et al. 2017

View full text Add to dashboard Cite

show abstract

“…These issues are further complicated by a surfeit of different EFA and CFA approaches to hierarchical model specification and estimation-some of which have only relatively recently been developed-as well as by issues such as empirical underidentification, where model estimability may be sample-dependent. As such, it is especially important for modelers to clarify whether or not a given bifactor structure is identified and specified (Eid et al 2017, Green & Yang 2017, Koch et al 2018, although further research in this area is needed, especially with hierarchical models including covariates and prediction.…”

Section: Conclusion and Recommendationsmentioning

confidence: 99%

Bifactor and Hierarchical Models: Specification, Inference, and Interpretation

Markon

2019

Annu. Rev. Clin. Psychol.

162

143

View full text Add to dashboard Cite

Bifactor and other hierarchical models have become central to representing and explaining observations in psychopathology, health, and other areas of clinical science, as well as in the behavioral sciences more broadly. This prominence comes after a relatively rapid period of rediscovery, however, and certain features remain poorly understood. Here, hierarchical models are compared and contrasted with other models of superordinate structure, with a focus on implications for model comparisons and interpretation. Issues pertaining to the specification and estimation of bifactor and other hierarchical models are reviewed in exploratory as well as confirmatory modeling scenarios, as are emerging findings about model fit and selection. Bifactor and other hierarchical models provide a powerful mechanism for parsing shared and unique components of variance, but care is required in specifying and making inferences about them.

show abstract

“…As a next step, we plan to investigate causes and preventions of classroom disturbances according to our theoretical model. However, these analyses need to overcome further methodological challenges (Koch, Holtmann, Bohn, & Eid, 2017).…”

Section: Research Perspectivesmentioning

confidence: 99%

Production and Perception of Classroom Disturbances

Eckstein

2019

FLR

View full text Add to dashboard Cite

Classroom disturbances impair the quality of teaching and learning, and they can be a source of strain for both teachers and students. Some studies indicate, however, that not everyone involved gets equally disturbed by the same occurrences. Altogether, there is still little solid knowledge about the teachers' and the students' subjective perception of disturbance. Moreover, rater effects may have confounded the findings available. Addressing these desiderata, the SUGUS study investigates two elements of classroom disturbances within an interactionist framework: the incidence of deviant behaviour shown by particular target students, and the intensity of disturbance as subjectively perceived by teachers, by classmates, and by the targets themselves. For this purpose, we conducted a questionnaire survey among 85 primary-school class teachers and 1412 students. The data were analysed by means of a two-level correlated traitcorrelated method minus one [CT-C(M-1)] model. This relatively novel statistical procedure has only rarely been applied in educational research so far. It made it possible to determine the respondents' common view on classroom disturbances as well as the rater-specific perspectives. The results indicate that increasing deviance coincides with increasing distraction and annoyance-but mainly in a relatively small intersection of the different perspectives. Beyond that, the analysis revealed substantial rater effects which explain 30 to 61% of variance in teacher ratings, for instance. The author discusses likely reasons why disturbances are perceived so divergently.

show abstract

Explaining general and specific factors in longitudinal, multimethod, and bifactor models: Some caveats and recommendations.

Cited by 52 publications

References 45 publications

The cross-national structure of mental disorders: results from the World Mental Health Surveys

The cross-national structure of mental disorders: results from the World Mental Health Surveys

Bifactor and Hierarchical Models: Specification, Inference, and Interpretation

Production and Perception of Classroom Disturbances

Contact Info

Product

Resources

About