Premium
Advantages of mixed effects models over traditional ANOVA models in developmental studies: A worked example in a mouse model of fetal alcohol syndrome
Author(s) -
Wainwright Patricia E.,
Leatherdale Scott T.,
Dubin Joel A.
Publication year - 2007
Publication title -
developmental psychobiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.055
H-Index - 93
eISSN - 1098-2302
pISSN - 0012-1630
DOI - 10.1002/dev.20245
Subject(s) - analysis of variance , repeated measures design , mixed model , context (archaeology) , litter , correlation , multilevel model , psychology , rat model , developmental psychology , statistics , mathematics , biology , endocrinology , ecology , paleontology , geometry
Developmental studies in animals often violate the assumption of statistical independence of observations due to the hierarchical nature of the data (i.e., pups cluster by litter, correlation of individual observations over time). Mixed effect modeling (MEM) provides a robust analytical approach for addressing problems associated with hierarchical data. This article compares the application of MEM to traditional ANOVA models within the context of a developmental study of prenatal ethanol exposure in mice. The results of the MEM analyses supported the ANOVA results in showing that a large proportion of the variability in both behavioral score and brain weight could be explained by ethanol. The MEM also identified that there were significant interactions between ethanol and litter size in relation to behavioral scores and brain weight. In addition, the longitudinal modeling approach using linear MEM allowed us to model for flexible weight gain over time, as well as to provide precise estimates of these effects, which would be difficult in repeated measures ANOVA. © 2007 Wiley Periodicals, Inc. Dev Psychobiol 49: 664–674, 2007.