Power of models in longitudinal study: Findings from a full-crossed simulation design

Hua Fang, Gordon Brooks, Maria Rizzo, Kimberly Andrews Espy, Robert Barcikowski

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Because the power properties of traditional repeated measures and hierarchical multivariate linear models have not been clearly determined in the balanced design for longitudinal studies in the literature, the authors present a power comparison study of traditional repeated measures and hierarchical multivariate linear models under 3 variance-covariance structures. The results from a full-crossed simulation design suggest that traditional repeated measures have significantly higher power than do hierarchical multivariate linear models for main effects, but they have significantly lower power for interaction effects in most situations. Significant power differences are also exhibited when power is compared across different covariance structures.

Original languageEnglish (US)
Pages (from-to)215-254
Number of pages40
JournalJournal of Experimental Education
Volume77
Issue number3
DOIs
StatePublished - Apr 1 2009
Externally publishedYes

Fingerprint

Longitudinal Studies
Linear Models
longitudinal study
linear model
simulation
interaction

Keywords

  • Covariance structure
  • Hierarchical multivariate linear models
  • Longitudinal study
  • Power analysis
  • Traditional repeated measures

ASJC Scopus subject areas

  • Education
  • Developmental and Educational Psychology

Cite this

Power of models in longitudinal study : Findings from a full-crossed simulation design. / Fang, Hua; Brooks, Gordon; Rizzo, Maria; Espy, Kimberly Andrews; Barcikowski, Robert.

In: Journal of Experimental Education, Vol. 77, No. 3, 01.04.2009, p. 215-254.

Research output: Contribution to journalArticle

Fang, Hua ; Brooks, Gordon ; Rizzo, Maria ; Espy, Kimberly Andrews ; Barcikowski, Robert. / Power of models in longitudinal study : Findings from a full-crossed simulation design. In: Journal of Experimental Education. 2009 ; Vol. 77, No. 3. pp. 215-254.
@article{f5a4d2894bbe4bcf9534dae4b7c8775a,
title = "Power of models in longitudinal study: Findings from a full-crossed simulation design",
abstract = "Because the power properties of traditional repeated measures and hierarchical multivariate linear models have not been clearly determined in the balanced design for longitudinal studies in the literature, the authors present a power comparison study of traditional repeated measures and hierarchical multivariate linear models under 3 variance-covariance structures. The results from a full-crossed simulation design suggest that traditional repeated measures have significantly higher power than do hierarchical multivariate linear models for main effects, but they have significantly lower power for interaction effects in most situations. Significant power differences are also exhibited when power is compared across different covariance structures.",
keywords = "Covariance structure, Hierarchical multivariate linear models, Longitudinal study, Power analysis, Traditional repeated measures",
author = "Hua Fang and Gordon Brooks and Maria Rizzo and Espy, {Kimberly Andrews} and Robert Barcikowski",
year = "2009",
month = "4",
day = "1",
doi = "10.3200/JEXE.77.3.215-254",
language = "English (US)",
volume = "77",
pages = "215--254",
journal = "Journal of Experimental Education",
issn = "0022-0973",
publisher = "Routledge",
number = "3",

}

TY - JOUR

T1 - Power of models in longitudinal study

T2 - Findings from a full-crossed simulation design

AU - Fang, Hua

AU - Brooks, Gordon

AU - Rizzo, Maria

AU - Espy, Kimberly Andrews

AU - Barcikowski, Robert

PY - 2009/4/1

Y1 - 2009/4/1

N2 - Because the power properties of traditional repeated measures and hierarchical multivariate linear models have not been clearly determined in the balanced design for longitudinal studies in the literature, the authors present a power comparison study of traditional repeated measures and hierarchical multivariate linear models under 3 variance-covariance structures. The results from a full-crossed simulation design suggest that traditional repeated measures have significantly higher power than do hierarchical multivariate linear models for main effects, but they have significantly lower power for interaction effects in most situations. Significant power differences are also exhibited when power is compared across different covariance structures.

AB - Because the power properties of traditional repeated measures and hierarchical multivariate linear models have not been clearly determined in the balanced design for longitudinal studies in the literature, the authors present a power comparison study of traditional repeated measures and hierarchical multivariate linear models under 3 variance-covariance structures. The results from a full-crossed simulation design suggest that traditional repeated measures have significantly higher power than do hierarchical multivariate linear models for main effects, but they have significantly lower power for interaction effects in most situations. Significant power differences are also exhibited when power is compared across different covariance structures.

KW - Covariance structure

KW - Hierarchical multivariate linear models

KW - Longitudinal study

KW - Power analysis

KW - Traditional repeated measures

UR - http://www.scopus.com/inward/record.url?scp=67649594943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649594943&partnerID=8YFLogxK

U2 - 10.3200/JEXE.77.3.215-254

DO - 10.3200/JEXE.77.3.215-254

M3 - Article

AN - SCOPUS:67649594943

VL - 77

SP - 215

EP - 254

JO - Journal of Experimental Education

JF - Journal of Experimental Education

SN - 0022-0973

IS - 3

ER -