Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Date of Graduation
Spring 2012
Document Type
Thesis
Degree Name
Master of Arts (MA)
Department
Department of Graduate Psychology
Abstract
Repeated measures analysis of variance (ANOVA) and multivariate analysis of variance (MANOVA) are two of the most common techniques employed in longitudinal data analysis. These methods, however, are extremely limited in the type of data permitted in analysis, the residual covariance matrices employed in analysis, as well as in the focus of the research questions. There are, however, modern techniques for analyzing longitudinal data that do not have the same limitations of repeated measures ANOVA and MANOVA. This study aims to compare traditional methods of analyzing longitudinal data with more modern techniques, including alternative covariance structure (ACS) modeling and multilevel modeling (MLM), through an example involving Sense of Identity in college students. This is done by first exploring assumptions of traditional and modern methods of analyzing longitudinal data. Next, an introduction to the identity literature is provided. The concept of residuals in between- and within-subjects analyses is then discussed. Finally, both traditional and modern techniques are employed to analyze the Sense of Identity data and results are compared and contrasted in an attempt to demonstrate the utility and benefits of more advanced techniques in longitudinal data analysis.
Recommended Citation
Samonte, Kelli Marie, "Should we change the way we model change? Comparing traditional and modern techniques in modeling change in sense of identity over time" (2012). Masters Theses, 2010-2019. 311.
https://commons.lib.jmu.edu/master201019/311