Multilevel and Single-Level Models for Measured and Latent Variables When Data Are Clustered

Laura M. Stapleton, Daniel McNeish, Ji Seung Yang

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate and advantageous to analyze such nested data within a single-level framework and when utilization of multilevel models presents advantages. The decision hinges on the research questions to be addressed, the scope of the data, and the measurement structure of any constructs hypothesized at the cluster level (Kozolowski & Klein, 2000; Marsh et al., 2012). We demonstrate models using several different data sets, including single-level and multilevel hierarchical linear models and confirmatory factor models. For these demonstrations, observational data from students nested within schools are used, as well as data from a classroom-based cluster randomized trial.

Original languageEnglish (US)
Pages (from-to)317-330
Number of pages14
JournalEducational Psychologist
Volume51
Issue number3-4
DOIs
StatePublished - Oct 1 2016
Externally publishedYes

Fingerprint

Wetlands
Linear Models
Students
Research
Datasets

ASJC Scopus subject areas

  • Developmental and Educational Psychology

Cite this

Multilevel and Single-Level Models for Measured and Latent Variables When Data Are Clustered. / Stapleton, Laura M.; McNeish, Daniel; Yang, Ji Seung.

In: Educational Psychologist, Vol. 51, No. 3-4, 01.10.2016, p. 317-330.

Research output: Contribution to journalArticle

@article{42957b79cb56440ca4308a748a276889,
title = "Multilevel and Single-Level Models for Measured and Latent Variables When Data Are Clustered",
abstract = "Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate and advantageous to analyze such nested data within a single-level framework and when utilization of multilevel models presents advantages. The decision hinges on the research questions to be addressed, the scope of the data, and the measurement structure of any constructs hypothesized at the cluster level (Kozolowski & Klein, 2000; Marsh et al., 2012). We demonstrate models using several different data sets, including single-level and multilevel hierarchical linear models and confirmatory factor models. For these demonstrations, observational data from students nested within schools are used, as well as data from a classroom-based cluster randomized trial.",
author = "Stapleton, {Laura M.} and Daniel McNeish and Yang, {Ji Seung}",
year = "2016",
month = "10",
day = "1",
doi = "10.1080/00461520.2016.1207178",
language = "English (US)",
volume = "51",
pages = "317--330",
journal = "Educational Psychologist",
issn = "0046-1520",
publisher = "Routledge",
number = "3-4",

}

TY - JOUR

T1 - Multilevel and Single-Level Models for Measured and Latent Variables When Data Are Clustered

AU - Stapleton, Laura M.

AU - McNeish, Daniel

AU - Yang, Ji Seung

PY - 2016/10/1

Y1 - 2016/10/1

N2 - Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate and advantageous to analyze such nested data within a single-level framework and when utilization of multilevel models presents advantages. The decision hinges on the research questions to be addressed, the scope of the data, and the measurement structure of any constructs hypothesized at the cluster level (Kozolowski & Klein, 2000; Marsh et al., 2012). We demonstrate models using several different data sets, including single-level and multilevel hierarchical linear models and confirmatory factor models. For these demonstrations, observational data from students nested within schools are used, as well as data from a classroom-based cluster randomized trial.

AB - Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate and advantageous to analyze such nested data within a single-level framework and when utilization of multilevel models presents advantages. The decision hinges on the research questions to be addressed, the scope of the data, and the measurement structure of any constructs hypothesized at the cluster level (Kozolowski & Klein, 2000; Marsh et al., 2012). We demonstrate models using several different data sets, including single-level and multilevel hierarchical linear models and confirmatory factor models. For these demonstrations, observational data from students nested within schools are used, as well as data from a classroom-based cluster randomized trial.

UR - http://www.scopus.com/inward/record.url?scp=84985031147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84985031147&partnerID=8YFLogxK

U2 - 10.1080/00461520.2016.1207178

DO - 10.1080/00461520.2016.1207178

M3 - Article

AN - SCOPUS:84985031147

VL - 51

SP - 317

EP - 330

JO - Educational Psychologist

JF - Educational Psychologist

SN - 0046-1520

IS - 3-4

ER -