A general multilevel SEM framework for assessing multilevel mediation

Kristopher J. Preacher, Michael J. Zyphur, Zhen Zhang

Research output: Contribution to journalArticle

1087 Citations (Scopus)

Abstract

Several methods for testing mediation hypotheses with 2-level nested data have been proposed by researchers using a multilevel modeling (MLM) paradigm. However, these MLM approaches do not accommodate mediation pathways with Level-2 outcomes and may produce conflated estimates of between- and within-level components of indirect effects. Moreover, these methods have each appeared in isolation, so a unified framework that integrates the existing methods, as well as new multilevel mediation models, is lacking. Here we show that a multilevel structural equation modeling (MSEM) paradigm can overcome these 2 limitations of mediation analysis with MLM. We present an integrative 2-level MSEM mathematical framework that subsumes new and existing multilevel mediation approaches as special cases. We use several applied examples and accompanying software code to illustrate the flexibility of this framework and to show that different substantive conclusions can be drawn using MSEM versus MLM.

Original languageEnglish (US)
Pages (from-to)209-233
Number of pages25
JournalPsychological Methods
Volume15
Issue number3
DOIs
StatePublished - Sep 2010

Fingerprint

Multilevel Analysis
Software
Research Personnel
Mediation
Multilevel Modeling
Structural Equation Modeling
Paradigm
Pathway
Isolation
Testing

Keywords

  • Mediation
  • Multilevel modeling
  • Multilevel SEM
  • Structural equation modeling

ASJC Scopus subject areas

  • Psychology (miscellaneous)
  • History and Philosophy of Science

Cite this

A general multilevel SEM framework for assessing multilevel mediation. / Preacher, Kristopher J.; Zyphur, Michael J.; Zhang, Zhen.

In: Psychological Methods, Vol. 15, No. 3, 09.2010, p. 209-233.

Research output: Contribution to journalArticle

Preacher, Kristopher J. ; Zyphur, Michael J. ; Zhang, Zhen. / A general multilevel SEM framework for assessing multilevel mediation. In: Psychological Methods. 2010 ; Vol. 15, No. 3. pp. 209-233.
@article{d3e84a7a17964bf899696e37d595a0d6,
title = "A general multilevel SEM framework for assessing multilevel mediation",
abstract = "Several methods for testing mediation hypotheses with 2-level nested data have been proposed by researchers using a multilevel modeling (MLM) paradigm. However, these MLM approaches do not accommodate mediation pathways with Level-2 outcomes and may produce conflated estimates of between- and within-level components of indirect effects. Moreover, these methods have each appeared in isolation, so a unified framework that integrates the existing methods, as well as new multilevel mediation models, is lacking. Here we show that a multilevel structural equation modeling (MSEM) paradigm can overcome these 2 limitations of mediation analysis with MLM. We present an integrative 2-level MSEM mathematical framework that subsumes new and existing multilevel mediation approaches as special cases. We use several applied examples and accompanying software code to illustrate the flexibility of this framework and to show that different substantive conclusions can be drawn using MSEM versus MLM.",
keywords = "Mediation, Multilevel modeling, Multilevel SEM, Structural equation modeling",
author = "Preacher, {Kristopher J.} and Zyphur, {Michael J.} and Zhen Zhang",
year = "2010",
month = "9",
doi = "10.1037/a0020141",
language = "English (US)",
volume = "15",
pages = "209--233",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "3",

}

TY - JOUR

T1 - A general multilevel SEM framework for assessing multilevel mediation

AU - Preacher, Kristopher J.

AU - Zyphur, Michael J.

AU - Zhang, Zhen

PY - 2010/9

Y1 - 2010/9

N2 - Several methods for testing mediation hypotheses with 2-level nested data have been proposed by researchers using a multilevel modeling (MLM) paradigm. However, these MLM approaches do not accommodate mediation pathways with Level-2 outcomes and may produce conflated estimates of between- and within-level components of indirect effects. Moreover, these methods have each appeared in isolation, so a unified framework that integrates the existing methods, as well as new multilevel mediation models, is lacking. Here we show that a multilevel structural equation modeling (MSEM) paradigm can overcome these 2 limitations of mediation analysis with MLM. We present an integrative 2-level MSEM mathematical framework that subsumes new and existing multilevel mediation approaches as special cases. We use several applied examples and accompanying software code to illustrate the flexibility of this framework and to show that different substantive conclusions can be drawn using MSEM versus MLM.

AB - Several methods for testing mediation hypotheses with 2-level nested data have been proposed by researchers using a multilevel modeling (MLM) paradigm. However, these MLM approaches do not accommodate mediation pathways with Level-2 outcomes and may produce conflated estimates of between- and within-level components of indirect effects. Moreover, these methods have each appeared in isolation, so a unified framework that integrates the existing methods, as well as new multilevel mediation models, is lacking. Here we show that a multilevel structural equation modeling (MSEM) paradigm can overcome these 2 limitations of mediation analysis with MLM. We present an integrative 2-level MSEM mathematical framework that subsumes new and existing multilevel mediation approaches as special cases. We use several applied examples and accompanying software code to illustrate the flexibility of this framework and to show that different substantive conclusions can be drawn using MSEM versus MLM.

KW - Mediation

KW - Multilevel modeling

KW - Multilevel SEM

KW - Structural equation modeling

UR - http://www.scopus.com/inward/record.url?scp=77956838713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956838713&partnerID=8YFLogxK

U2 - 10.1037/a0020141

DO - 10.1037/a0020141

M3 - Article

VL - 15

SP - 209

EP - 233

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 3

ER -