Bifactor Models for Predicting Criteria by General and Specific Factors: Problems of Nonidentifiability and Alternative Solutions

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Bifactor Models for Predicting Criteria by General and Specific Factors: Problems of Nonidentifiability and Alternative Solutions. / Eid, Michael; Krumm, Stefan; Koch, Tobias et al.
in: Intelligence, Jahrgang 6, Nr. 3, 42, 07.09.2018.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{2f06f82288b446608dffa2942db438dc,
title = "Bifactor Models for Predicting Criteria by General and Specific Factors: Problems of Nonidentifiability and Alternative Solutions",
abstract = "The bifactor model is a widely applied model to analyze general and specific abilities. Extensions of bifactor models additionally include criterion variables. In such extended bifactor models, the general and specific factors can be correlated with criterion variables. Moreover, the influence of general and specific factors on criterion variables can be scrutinized in latent multiple regression models that are built on bifactor measurement models. This study employs an extended bifactor model to predict mathematics and English grades by three facets of intelligence (number series, verbal analogies, and unfolding). We show that, if the observed variables do not differ in their loadings, extended bifactor models are not identified and not applicable. Moreover, we reveal that standard errors of regression weights in extended bifactor models can be very large and, thus, lead to invalid conclusions. A formal proof of the nonidentification is presented. Subsequently, we suggest alternative approaches for predicting criterion variables by general and specific factors. In particular, we illustrate how (1) composite ability factors can be defined in extended first-order factor models and (2) how bifactor(S-1) models can be applied. The differences between first-order factor models and bifactor(S-1) models for predicting criterion variables are discussed in detail and illustrated with the empirical example.",
keywords = "Social Work and Social Pedagogics, bifactor model, identification, bifactor (s-1) model, general factor, specific factors, Sociology",
author = "Michael Eid and Stefan Krumm and Tobias Koch and Julian Schulze",
note = "Publisher Copyright: {\textcopyright} 2018 by the authors. Licensee MDPI, Basel, Switzerland.",
year = "2018",
month = sep,
day = "7",
doi = "10.3390/jintelligence6030042",
language = "English",
volume = "6",
journal = "Intelligence",
issn = "0160-2896",
publisher = "Elsevier Ltd",
number = "3",

}

RIS

TY - JOUR

T1 - Bifactor Models for Predicting Criteria by General and Specific Factors

T2 - Problems of Nonidentifiability and Alternative Solutions

AU - Eid, Michael

AU - Krumm, Stefan

AU - Koch, Tobias

AU - Schulze, Julian

N1 - Publisher Copyright: © 2018 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2018/9/7

Y1 - 2018/9/7

N2 - The bifactor model is a widely applied model to analyze general and specific abilities. Extensions of bifactor models additionally include criterion variables. In such extended bifactor models, the general and specific factors can be correlated with criterion variables. Moreover, the influence of general and specific factors on criterion variables can be scrutinized in latent multiple regression models that are built on bifactor measurement models. This study employs an extended bifactor model to predict mathematics and English grades by three facets of intelligence (number series, verbal analogies, and unfolding). We show that, if the observed variables do not differ in their loadings, extended bifactor models are not identified and not applicable. Moreover, we reveal that standard errors of regression weights in extended bifactor models can be very large and, thus, lead to invalid conclusions. A formal proof of the nonidentification is presented. Subsequently, we suggest alternative approaches for predicting criterion variables by general and specific factors. In particular, we illustrate how (1) composite ability factors can be defined in extended first-order factor models and (2) how bifactor(S-1) models can be applied. The differences between first-order factor models and bifactor(S-1) models for predicting criterion variables are discussed in detail and illustrated with the empirical example.

AB - The bifactor model is a widely applied model to analyze general and specific abilities. Extensions of bifactor models additionally include criterion variables. In such extended bifactor models, the general and specific factors can be correlated with criterion variables. Moreover, the influence of general and specific factors on criterion variables can be scrutinized in latent multiple regression models that are built on bifactor measurement models. This study employs an extended bifactor model to predict mathematics and English grades by three facets of intelligence (number series, verbal analogies, and unfolding). We show that, if the observed variables do not differ in their loadings, extended bifactor models are not identified and not applicable. Moreover, we reveal that standard errors of regression weights in extended bifactor models can be very large and, thus, lead to invalid conclusions. A formal proof of the nonidentification is presented. Subsequently, we suggest alternative approaches for predicting criterion variables by general and specific factors. In particular, we illustrate how (1) composite ability factors can be defined in extended first-order factor models and (2) how bifactor(S-1) models can be applied. The differences between first-order factor models and bifactor(S-1) models for predicting criterion variables are discussed in detail and illustrated with the empirical example.

KW - Social Work and Social Pedagogics

KW - bifactor model

KW - identification

KW - bifactor (s-1) model

KW - general factor

KW - specific factors

KW - Sociology

UR - http://www.scopus.com/inward/record.url?scp=85074341125&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/f315784d-ea5b-3f1f-8fc8-b84595352b2b/

U2 - 10.3390/jintelligence6030042

DO - 10.3390/jintelligence6030042

M3 - Journal articles

C2 - 31162469

VL - 6

JO - Intelligence

JF - Intelligence

SN - 0160-2896

IS - 3

M1 - 42

ER -

Dokumente

DOI

Zuletzt angesehen

Projekte

  1. Research Lab

Aktivitäten

  1. 2. Ludotopia Workshop 2011
  2. Personalising the impersonal: Interaction in public information messages across cultures (Universität Bayreuth, invited talk)
  3. The Implementation and Future Challenges of Education for Sustainable Development in Germany
  4. The Paradox of Openness
  5. Moral responsibility, motivational crowding, and efficient regulation of externalities
  6. „Positiv/Negativ – Dialog“
  7. Management Control in Supply Chain Management: A Concept and first Empirical Insights
  8. Remixing Digital Cities
  9. Monomers release from composite materials after halogen and LED curing.
  10. How working from home impairs recovery from work: Anticipated availability as a cognitive process in the stressor-detachment model
  11. Indigenous Protests and the Environment
  12. Management Learning (Fachzeitschrift)
  13. Elution of monomers from two composite resins.
  14. Studies in Space Law (Zeitschrift)
  15. EURISY: Models of Governance of National Space Activities in the Evolving European Framework 2009
  16. The Seventh International Conference on Task-Based Language Teaching 2017
  17. Frame Conditions for Transdisciplinary Research. Transdisciplinary and historical rural and urban spatial transformation and development (TRUST)
  18. Alcohol myopia and gambling behavior
  19. Virtual Songwriting. Fostering Creative Processes through „Challenge“ and „Collaboration“.
  20. Organizing ‘Safe Spaces’ for Creative Collaboration
  21. International Federation for Information Processing (ifip) (Externe Organisation)
  22. Affective Human-Robot Interaction – The Influence of Humans’ Emotion Recognition Ability