Graphical and statistical methods for the analysis of repeated measures data

Repeated measures designs are used commonly in research studies. The main advantage to this type of design is that it allows for the study of change over time. Furthermore, a reduction in unexplained variability in the response is achieved with each subject serving as his or her own control.; The problem with analyzing repeated measures data is that measurements taken on the same individual are usually correlated. This lack of independence violates the assumptions inherent in many common types of analyses, requiring alternate methods to be applied.; The main goal of this thesis is to illustrate a variety of graphical and statistical approaches available for analyzing repeated measures data. Graphical displays considered include plotting summary values, individual profile plots, box plots, and bar graphs. Simple univariate analyses as well as more sophisticated modelling techniques, including univariate repeated measures analysis of variance and generalized estimating equations, are discussed.