Mixed effects modeling of Morris water maze data

Advantages and cautionary notes

Michael E. Young, M. H. Clark, Andrea Goffus, Michael R. Hoane

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Morris water maze data are most commonly analyzed using repeated measures analysis of variance in which daily test sessions are analyzed as an unordered categorical variable. This approach, however, may lack power, relies heavily on post hoc tests of daily performance that can complicate interpretation, and does not target the nonlinear trends evidenced in learning data. The present project used Monte Carlo simulation to compare the relative strengths of the traditional approach with both linear and nonlinear mixed effects modeling that identifies the learning function for each animal and condition. Both trend-based mixed effects modeling approaches showed much greater sensitivity to identifying real effects, and the nonlinear approach provided uniformly better fits of learning trends. The common practice of removing a rat from the maze after 90 s, however, proved more problematic for the nonlinear approach and produced an underestimate of y-axis intercepts.

Original languageEnglish (US)
Pages (from-to)160-177
Number of pages18
JournalLearning and Motivation
Volume40
Issue number2
DOIs
StatePublished - May 1 2009
Externally publishedYes

Fingerprint

Learning
water
Water
trend
learning
analysis of variance
Analysis of Variance
animal
simulation
interpretation
lack
performance
Power (Psychology)

Keywords

  • Learning curves
  • Monte Carlo simulation
  • Nonlinear analysis
  • Repeated measures

ASJC Scopus subject areas

  • Health(social science)
  • Neuropsychology and Physiological Psychology
  • Experimental and Cognitive Psychology
  • Education
  • Developmental and Educational Psychology

Cite this

Mixed effects modeling of Morris water maze data : Advantages and cautionary notes. / Young, Michael E.; Clark, M. H.; Goffus, Andrea; Hoane, Michael R.

In: Learning and Motivation, Vol. 40, No. 2, 01.05.2009, p. 160-177.

Research output: Contribution to journalArticle

Young, Michael E. ; Clark, M. H. ; Goffus, Andrea ; Hoane, Michael R. / Mixed effects modeling of Morris water maze data : Advantages and cautionary notes. In: Learning and Motivation. 2009 ; Vol. 40, No. 2. pp. 160-177.
@article{aca0c95a7ef6490d87f853df00e31df2,
title = "Mixed effects modeling of Morris water maze data: Advantages and cautionary notes",
abstract = "Morris water maze data are most commonly analyzed using repeated measures analysis of variance in which daily test sessions are analyzed as an unordered categorical variable. This approach, however, may lack power, relies heavily on post hoc tests of daily performance that can complicate interpretation, and does not target the nonlinear trends evidenced in learning data. The present project used Monte Carlo simulation to compare the relative strengths of the traditional approach with both linear and nonlinear mixed effects modeling that identifies the learning function for each animal and condition. Both trend-based mixed effects modeling approaches showed much greater sensitivity to identifying real effects, and the nonlinear approach provided uniformly better fits of learning trends. The common practice of removing a rat from the maze after 90 s, however, proved more problematic for the nonlinear approach and produced an underestimate of y-axis intercepts.",
keywords = "Learning curves, Monte Carlo simulation, Nonlinear analysis, Repeated measures",
author = "Young, {Michael E.} and Clark, {M. H.} and Andrea Goffus and Hoane, {Michael R.}",
year = "2009",
month = "5",
day = "1",
doi = "10.1016/j.lmot.2008.10.004",
language = "English (US)",
volume = "40",
pages = "160--177",
journal = "Learning and Motivation",
issn = "0023-9690",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Mixed effects modeling of Morris water maze data

T2 - Advantages and cautionary notes

AU - Young, Michael E.

AU - Clark, M. H.

AU - Goffus, Andrea

AU - Hoane, Michael R.

PY - 2009/5/1

Y1 - 2009/5/1

N2 - Morris water maze data are most commonly analyzed using repeated measures analysis of variance in which daily test sessions are analyzed as an unordered categorical variable. This approach, however, may lack power, relies heavily on post hoc tests of daily performance that can complicate interpretation, and does not target the nonlinear trends evidenced in learning data. The present project used Monte Carlo simulation to compare the relative strengths of the traditional approach with both linear and nonlinear mixed effects modeling that identifies the learning function for each animal and condition. Both trend-based mixed effects modeling approaches showed much greater sensitivity to identifying real effects, and the nonlinear approach provided uniformly better fits of learning trends. The common practice of removing a rat from the maze after 90 s, however, proved more problematic for the nonlinear approach and produced an underestimate of y-axis intercepts.

AB - Morris water maze data are most commonly analyzed using repeated measures analysis of variance in which daily test sessions are analyzed as an unordered categorical variable. This approach, however, may lack power, relies heavily on post hoc tests of daily performance that can complicate interpretation, and does not target the nonlinear trends evidenced in learning data. The present project used Monte Carlo simulation to compare the relative strengths of the traditional approach with both linear and nonlinear mixed effects modeling that identifies the learning function for each animal and condition. Both trend-based mixed effects modeling approaches showed much greater sensitivity to identifying real effects, and the nonlinear approach provided uniformly better fits of learning trends. The common practice of removing a rat from the maze after 90 s, however, proved more problematic for the nonlinear approach and produced an underestimate of y-axis intercepts.

KW - Learning curves

KW - Monte Carlo simulation

KW - Nonlinear analysis

KW - Repeated measures

UR - http://www.scopus.com/inward/record.url?scp=62549104201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62549104201&partnerID=8YFLogxK

U2 - 10.1016/j.lmot.2008.10.004

DO - 10.1016/j.lmot.2008.10.004

M3 - Article

VL - 40

SP - 160

EP - 177

JO - Learning and Motivation

JF - Learning and Motivation

SN - 0023-9690

IS - 2

ER -