Three Concerns With Applying a Bifactor Model as a Structure of Psychopathology

Bonifay, Wes; Lane, Sean P.; Reise, Steven P.

doi:10.1177/2167702616657069

Cited by 350 publications

(375 citation statements)

References 18 publications

Supporting

Mentioning

350

Contrasting

Unclassified

Order By: Relevance

“…Bifactor models have been criticized for the tendency to show superior goodness-of-fit to alternative models due to a higher number of free parameters (Bonifay, Lane, & Reise, 2017). On the other hand, a bifactor approach can shed light on the structure of measures by modelling shared and unique variance amongst items, which is defensible when theoretically justified as is the case for the construct of clinical perfectionism and with a measure with a complex (i.e., crossloadings) factor structure (Bonifay et al, 2017). It is also important to note that bifactor modelling, and CFA more generally, sheds light on the latent structure of a measure, but does not allow conclusions to be drawn about the nature of the construct of clinical perfectionism (e.g., critical components may not be measured by the CPQ).…”

Section: Discussionmentioning

confidence: 99%

Validation of the clinical perfectionism questionnaire in an eating disorder sample: A bifactor approach

Prior

Erceg‐Hurn

Raykos

et al. 2018

Intl J Eating Disorders

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Validation of the clinical perfectionism questionnaire in an eating disorder sample: A bifactor approach

Prior

Erceg‐Hurn

Raykos

et al. 2018

Intl J Eating Disorders

View full text Add to dashboard Cite

show abstract

“…In this paper, we report the results of new factor analyses of item-level data from parent ratings of child behavior and emotions as well as tests of criterion validity using both models in the Adolescent Brain Cognitive Development (ABCD) Study (Volkow et al, 2018). These headto-head empirical comparisons are conducted following strict requirements suggested for bifactor modeling (Bonifay, Lane, & Reise, 2017;Bornovalova et al, 2020;Sellbom & Tellegen, 2019):…”

Section: General Scientific Summarymentioning

confidence: 99%

“…Each model fit the data well (Table S10). Because of difficulties in choosing between substantively different models that fit the data well using fit statistics, we evaluated the two structural models in terms of their criterion validity (Bonifay et al, 2017;Greene et al, 2019). Table 1, all factors in both models had acceptable H indices >0.70 (Hancock & Mueller, 2001) and each specific factor in the bifactor models was reliable according to omega statistics.…”

Section: Confirmatory Factor Analyses In the Second Half Of The Samplementioning

confidence: 99%

Criterion Validity and Relationships between Alternative Hierarchical Dimensional Models of General and Specific Psychopathology

Moore

Kaczkurkin

Durham

et al. 2020

Preprint

View full text Add to dashboard Cite

Psychopathology can be viewed as a hierarchy of correlated dimensions. Many studies have supported this conceptualization, but they have used alternative statistical models with differing interpretations. In bifactor models, every symptom loads on both the general factor and one specific factor (e.g., internalizing), which partitions the total explained variance in each symptom between these orthogonal factors. In second-order models, symptoms load on one of several correlated lower-order factors. These lower-order factors load on a second-order general factor, which is defined by the variance shared by the lower-order factors. Thus, the factors in secondorder models are not orthogonal. Choosing between these valid statistical models depends on the hypothesis being tested. Because bifactor models define orthogonal phenotypes with distinct sources of variance, they are optimal for studies of shared and unique associations of the dimensions of psychopathology with external variables putatively relevant to etiology and mechanisms. Concerns have been raised, however, about the reliability of the orthogonal specific factors in bifactor models. We evaluated this concern using parent symptom ratings of 9-10 year olds in the ABCD Study. Psychometric indices indicated that all factors in both bifactor and second-order models exhibited at least adequate construct reliability and estimated replicability.The factors defined in bifactor and second-order models were highly to moderately correlated across models, but have different interpretations. All factors in both models demonstrated significant associations with external criterion variables of theoretical and clinical importance, but the interpretation of such associations in second-order models was ambiguous due to shared variance among factors.

show abstract

“…La razón es sencilla: aunque el FG resulte más robusto que los FEs, si carece de una interpretación teórica coherente por sí mismo, no ene sen do considerarlo y sería mejor interpretar cada FE por separado (Bonifay, Lane, & Reise, 2017;Moscoso, Merino-Soto, DominguezLara, Chau, & Claux, 2016).…”

Section: Comentarios Finalesunclassified

Índices estadísticos de modelos bifactor

Domínguez-Lara

Rodriguez²

2017

Interacciones

View full text Add to dashboard Cite

BY CrossMarkclick for updates iD iD RESUMENMuchos instrumentos se crean con el propósito principal de evaluar sujetos con relación a un solo rasgo. Sin embargo, los rasgos psicológicos son frecuentemente complejos y con enen manifestaciones de dominio específico. Como tal, muchos instrumentos brindan información que son consistentes tanto con las estructuras unidimensionales como las mul dimensionales. Por desgracia, muchas veces, los inves gadores aplicados hacen determinaciones sobre la estructura final basado únicamente en los índices de ajuste obtenidos a par r de modelos de ecuaciones estructurales. Dado que los índices de ajuste generalmente favorecen al modelo bifactor sobre los modelos de medición compe dores, es impera vo que los inves gadores hacen uso de la información disponible que los modelos bifactor enen para ofrecer con el fin de calcular los índices informavos incluyendo coeficientes de confiabilidad omega, confiabilidad del constructo, varianza común explicada, y el porcentaje de correlaciones no contaminadas. Dichos índices proporcionan información acerca de la fuerza tanto de los factores generales como de los factores específicos con el fin de sacar conclusiones acerca de la dimensionalidad y la puntuación global de las escalas (y subescalas). En este documento, se describen estos índices y ofrecen un nuevo módulo que facilita su cálculo. PALABRAS CLAVE Análisis factorial confirmatorio;Bifactor;Omega; Confiabilidad del constructo;Varianza común explicada;Porcentaje de correlaciones no contaminadas. ISSN 2411-5940 (impreso) / e-ISSN 2413 Obra bajo licencia de

show abstract

Three Concerns With Applying a Bifactor Model as a Structure of Psychopathology

Cited by 350 publications

References 18 publications

Validation of the clinical perfectionism questionnaire in an eating disorder sample: A bifactor approach

Validation of the clinical perfectionism questionnaire in an eating disorder sample: A bifactor approach

Criterion Validity and Relationships between Alternative Hierarchical Dimensional Models of General and Specific Psychopathology

Índices estadísticos de modelos bifactor

Contact Info

Product

Resources

About