Premium
A comparison of traditional approaches to hierarchical linear modeling when analyzing longitudinal data
Author(s) -
Wu YowWu B.,
Clopper Richard R.,
Wooldridge Powhatan J.
Publication year - 1999
Publication title -
research in nursing and health
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.836
H-Index - 85
eISSN - 1098-240X
pISSN - 0160-6891
DOI - 10.1002/(sici)1098-240x(199910)22:5<421::aid-nur8>3.0.co;2-q
Subject(s) - univariate , longitudinal data , repeated measures design , multivariate statistics , contrast (vision) , linear model , multilevel model , computer science , longitudinal study , generalized linear mixed model , multivariate analysis , statistics , econometrics , data mining , machine learning , artificial intelligence , mathematics
Longitudinal designs typically involve repeated time‐ordered observations for each individual (or unit). Such designs are uniquely suited to studying changes over time within individuals, and relating these to individual characteristics to identify processes and causes of intra‐ individual changes and interindividual differences in physiologic and psychological development. The purpose of this paper is to compare and contrast univariate and multivariate ANOVA with repeated measures to hierarchical linear modeling as approaches to analyzing such longitudinal data. This will enable researchers to choose the approach that best meets their research needs, and it will enable them to compare research results that are reported using one analytical approach with results that are reported using the other approach. © 1999 John Wiley & Sons, Inc. Res Nurs Health 22:421–432, 1999