College - Author 1

College of Science and Mathematics

Department - Author 1

Statistics Department

Degree Name - Author 1

BS in Statistics

Date

6-2010

Primary Advisor

Jeffrey Sklar

Abstract/Summary

Multivariate analysis of variance (MANOVA) is most commonly used in the field of bio-statistics. Throughout this paper I conduct numerous simulations that help analyze how robust the MANOVA procedure is against its assumptions. Using Type I error rate as my measure of error, I used the R software to graph my results. The main assumption that is focused on is the equal covariance matrix assumption, which we introduce correlation between variables to see how well the MANOVA procedure performs. Overall, 70 simulations were ran, and 10 functions were created to perform all of the analysis.

Share

COinS