On the Power and Performance of a Doubly Latent Residual Approach to Explain Latent Specific Factors in Multilevel-Bifactor-(S-1) Models

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Harvard

APA

Vancouver

Bibtex

@article{9b33294cf7c944d382c516a1bb0bbc75,
title = "On the Power and Performance of a Doubly Latent Residual Approach to Explain Latent Specific Factors in Multilevel-Bifactor-(S-1) Models",
abstract = "A doubly latent residual approach (DLRA) is presented to explain latent specific factors in multilevel bifactor-(S-1) models. The new approach overcomes some important limitations of the multiple indicators multiple causes (MIMIC) approach and allows researchers to predict latent specific factors at different levels. The DLRA is illustrated using real data from a large-scale assessment study. Furthermore, the statistical performance and power of the DLRA is examined in a Monte Carlo simulation study. The results show that the new DLRA performs well if more than 50 clusters and more than 10 observations per cluster are sampled. The power to test structural parameters at level 2 was lower than at level 1. To test a medium effect at level 2, we recommend to sample at least 100 clusters with a minimum cluster size of 10. The advantages and limitations of the new approach are discussed and guidelines for applied researchers are provided.",
keywords = "Transdisciplinary studies, MIMIC approach, multilevel bifactor models, multilevel structural equation models, simulation study",
author = "Tobias Koch and Ulrike Semmler-Busch",
note = "This work was supported by the Deutsche Forschungsgemeinschaft [grant number KO4770/1-1]. Publisher Copyright: {\textcopyright} 2019, {\textcopyright} 2019 The Author(s). Published with license by Taylor & Francis Group, LLC.",
year = "2019",
month = mar,
day = "4",
doi = "10.1080/10705511.2018.1516506",
language = "English",
volume = "26",
pages = "212--235",
journal = "Structural Equation Modeling: A Multidisciplinary Journal",
issn = "1070-5511",
publisher = "Taylor & Francis",
number = "2",

}

RIS

TY - JOUR

T1 - On the Power and Performance of a Doubly Latent Residual Approach to Explain Latent Specific Factors in Multilevel-Bifactor-(S-1) Models

AU - Koch, Tobias

AU - Semmler-Busch, Ulrike

N1 - This work was supported by the Deutsche Forschungsgemeinschaft [grant number KO4770/1-1]. Publisher Copyright: © 2019, © 2019 The Author(s). Published with license by Taylor & Francis Group, LLC.

PY - 2019/3/4

Y1 - 2019/3/4

N2 - A doubly latent residual approach (DLRA) is presented to explain latent specific factors in multilevel bifactor-(S-1) models. The new approach overcomes some important limitations of the multiple indicators multiple causes (MIMIC) approach and allows researchers to predict latent specific factors at different levels. The DLRA is illustrated using real data from a large-scale assessment study. Furthermore, the statistical performance and power of the DLRA is examined in a Monte Carlo simulation study. The results show that the new DLRA performs well if more than 50 clusters and more than 10 observations per cluster are sampled. The power to test structural parameters at level 2 was lower than at level 1. To test a medium effect at level 2, we recommend to sample at least 100 clusters with a minimum cluster size of 10. The advantages and limitations of the new approach are discussed and guidelines for applied researchers are provided.

AB - A doubly latent residual approach (DLRA) is presented to explain latent specific factors in multilevel bifactor-(S-1) models. The new approach overcomes some important limitations of the multiple indicators multiple causes (MIMIC) approach and allows researchers to predict latent specific factors at different levels. The DLRA is illustrated using real data from a large-scale assessment study. Furthermore, the statistical performance and power of the DLRA is examined in a Monte Carlo simulation study. The results show that the new DLRA performs well if more than 50 clusters and more than 10 observations per cluster are sampled. The power to test structural parameters at level 2 was lower than at level 1. To test a medium effect at level 2, we recommend to sample at least 100 clusters with a minimum cluster size of 10. The advantages and limitations of the new approach are discussed and guidelines for applied researchers are provided.

KW - Transdisciplinary studies

KW - MIMIC approach

KW - multilevel bifactor models

KW - multilevel structural equation models

KW - simulation study

UR - http://www.scopus.com/inward/record.url?scp=85054050501&partnerID=8YFLogxK

U2 - 10.1080/10705511.2018.1516506

DO - 10.1080/10705511.2018.1516506

M3 - Journal articles

VL - 26

SP - 212

EP - 235

JO - Structural Equation Modeling: A Multidisciplinary Journal

JF - Structural Equation Modeling: A Multidisciplinary Journal

SN - 1070-5511

IS - 2

ER -

Documents

DOI