Alternative Models for Small Samples in Psychological Research: Applying Linear Mixed Effects Models and Generalized Estimating Equations to Repeated Measures Data

Chelsea Muth, Karen L. Bales, Katherine Hinde, Nicole Maninger, Sally P. Mendoza, Emilio Ferrer

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Unavoidable sample size issues beset psychological research that involves scarce populations or costly laboratory procedures. When incorporating longitudinal designs these samples are further reduced by traditional modeling techniques, which perform listwise deletion for any instance of missing data. Moreover, these techniques are limited in their capacity to accommodate alternative correlation structures that are common in repeated measures studies. Researchers require sound quantitative methods to work with limited but valuable measures without degrading their data sets. This article provides a brief tutorial and exploration of two alternative longitudinal modeling techniques, linear mixed effects models and generalized estimating equations, as applied to a repeated measures study (n = 12) of pairmate attachment and social stress in primates. Both techniques provide comparable results, but each model offers unique information that can be helpful when deciding the right analytic tool.

Original languageEnglish (US)
Pages (from-to)64-87
Number of pages24
JournalEducational and Psychological Measurement
Volume76
Issue number1
DOIs
StatePublished - Feb 1 2016
Externally publishedYes

Fingerprint

Linear Mixed Effects Model
Measure Data
Generalized Estimating Equations
Repeated Measures
Small Sample
Psychology
Alternatives
quantitative method
Research
Sample Size
Primates
Research Personnel
Acoustic waves
Correlation Structure
Missing Data
Modeling
Model
Population
Deletion
Datasets

Keywords

  • generalized estimating equations
  • linear mixed effects models
  • longitudinal data
  • repeated measures ANOVA
  • small sample

ASJC Scopus subject areas

  • Developmental and Educational Psychology
  • Education
  • Applied Psychology
  • Applied Mathematics

Cite this

Alternative Models for Small Samples in Psychological Research : Applying Linear Mixed Effects Models and Generalized Estimating Equations to Repeated Measures Data. / Muth, Chelsea; Bales, Karen L.; Hinde, Katherine; Maninger, Nicole; Mendoza, Sally P.; Ferrer, Emilio.

In: Educational and Psychological Measurement, Vol. 76, No. 1, 01.02.2016, p. 64-87.

Research output: Contribution to journalArticle

@article{c65d8afbfa094b5182e75f0ff4aecab1,
title = "Alternative Models for Small Samples in Psychological Research: Applying Linear Mixed Effects Models and Generalized Estimating Equations to Repeated Measures Data",
abstract = "Unavoidable sample size issues beset psychological research that involves scarce populations or costly laboratory procedures. When incorporating longitudinal designs these samples are further reduced by traditional modeling techniques, which perform listwise deletion for any instance of missing data. Moreover, these techniques are limited in their capacity to accommodate alternative correlation structures that are common in repeated measures studies. Researchers require sound quantitative methods to work with limited but valuable measures without degrading their data sets. This article provides a brief tutorial and exploration of two alternative longitudinal modeling techniques, linear mixed effects models and generalized estimating equations, as applied to a repeated measures study (n = 12) of pairmate attachment and social stress in primates. Both techniques provide comparable results, but each model offers unique information that can be helpful when deciding the right analytic tool.",
keywords = "generalized estimating equations, linear mixed effects models, longitudinal data, repeated measures ANOVA, small sample",
author = "Chelsea Muth and Bales, {Karen L.} and Katherine Hinde and Nicole Maninger and Mendoza, {Sally P.} and Emilio Ferrer",
year = "2016",
month = "2",
day = "1",
doi = "10.1177/0013164415580432",
language = "English (US)",
volume = "76",
pages = "64--87",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "1",

}

TY - JOUR

T1 - Alternative Models for Small Samples in Psychological Research

T2 - Applying Linear Mixed Effects Models and Generalized Estimating Equations to Repeated Measures Data

AU - Muth, Chelsea

AU - Bales, Karen L.

AU - Hinde, Katherine

AU - Maninger, Nicole

AU - Mendoza, Sally P.

AU - Ferrer, Emilio

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Unavoidable sample size issues beset psychological research that involves scarce populations or costly laboratory procedures. When incorporating longitudinal designs these samples are further reduced by traditional modeling techniques, which perform listwise deletion for any instance of missing data. Moreover, these techniques are limited in their capacity to accommodate alternative correlation structures that are common in repeated measures studies. Researchers require sound quantitative methods to work with limited but valuable measures without degrading their data sets. This article provides a brief tutorial and exploration of two alternative longitudinal modeling techniques, linear mixed effects models and generalized estimating equations, as applied to a repeated measures study (n = 12) of pairmate attachment and social stress in primates. Both techniques provide comparable results, but each model offers unique information that can be helpful when deciding the right analytic tool.

AB - Unavoidable sample size issues beset psychological research that involves scarce populations or costly laboratory procedures. When incorporating longitudinal designs these samples are further reduced by traditional modeling techniques, which perform listwise deletion for any instance of missing data. Moreover, these techniques are limited in their capacity to accommodate alternative correlation structures that are common in repeated measures studies. Researchers require sound quantitative methods to work with limited but valuable measures without degrading their data sets. This article provides a brief tutorial and exploration of two alternative longitudinal modeling techniques, linear mixed effects models and generalized estimating equations, as applied to a repeated measures study (n = 12) of pairmate attachment and social stress in primates. Both techniques provide comparable results, but each model offers unique information that can be helpful when deciding the right analytic tool.

KW - generalized estimating equations

KW - linear mixed effects models

KW - longitudinal data

KW - repeated measures ANOVA

KW - small sample

UR - http://www.scopus.com/inward/record.url?scp=84953426292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953426292&partnerID=8YFLogxK

U2 - 10.1177/0013164415580432

DO - 10.1177/0013164415580432

M3 - Article

AN - SCOPUS:84953426292

VL - 76

SP - 64

EP - 87

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 1

ER -