Off-campus WSU users: To download campus access dissertations, please use the following link to log into our proxy server with your WSU access ID and password, then click the "Off-campus Download" button below.
Non-WSU users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Access Type
WSU Access
Date of Award
January 2019
Degree Type
Dissertation
Degree Name
Ph.D.
Department
Education Evaluation and Research
First Advisor
Shlomo S. Sawilowsky
Abstract
Repeated Measures are often used in various social sciences such as education, business, and psychology to inform decisions on adopting new practices. There are several methods of analysis used to analyze repeated measures data, but the decision of which method is best for analysis is often unclear. Therefore, in this study, the researcher conducted a Monte Carlo simulation study of 100, 000 repetitions with samples drawn from the Normal, Chi-Square (df = 2), t (df = 3), and the Uniform distributions to assess the power of the Repeated Measures ANOVA, Friedman, Skillings-Mack, Neave and Worthington Match 1 and Match 2, Trimmed Means Repeated Measures ANOVA, and the Bootstrap Trimmed Means Repeated Measures ANOVA tests under correlation levels of 0.70, 0.80, and 0.90 for groups of k = 3 and 5 with subjects of n = 10, 30, and 50 per group. Results indicated that classical statistical methods showed power superiority over the modern statistical methods using trimmed means for most distributions, and the differences in perceived power for the Neave and Worthington Match tests over the Friedman and Skillings-Mack tests were not supported due to a non-robust Type I error.
Recommended Citation
Bosley, Tiana, "Comparative Power Of The Friedman, Neave And Worthington Match, Skillings-Mack, Trimmed Means Repeated Measures Anova, And Bootstrap Trimmed Means Repeated Measures Anova Tests" (2019). Wayne State University Dissertations. 2318.
https://digitalcommons.wayne.edu/oa_dissertations/2318