Date of Award:
Master of Science (MS)
Mathematics and Statistics
Graphical software packages have become increasingly popular in our modern world, but there are concerns within the statistical visualization field about the default settings provided by these packages, which can make it challenging to create good quality graphs that align with standard graph principles. In this thesis, we investigate whether the quality of graphs from Utah State University (USU) Plan A Master of Science (MS) thesis reports from the years 1930 to 2019 was affected by the rise of graphical software packages. We collected all data stored on the USU Digital Commons website since November 2021 to determine the specific group of graphs we wanted to investigate and developed a sampling process to obtain a sample size of 90 graphs evenly distributed over the time range. To accurately judge graph quality, we compiled and condensed good graphic standards from the statistical literature and developed our own set of graph quality criteria, grouped within four distinct categories: Labeling, Clear Understanding, Meaningful, and Scaling and Gridlines. We constructed a scoring system to rate the quality of graphs against these criteria and explored the results by constructing several visualizations and performing various statistical analyses. Our analysis assessed whether the rise of graphical software packages impacted the quality of graphs within the USU Plan A MS thesis reports.
Astle, Ragan, "Statistical Graph Quality Analysis of Utah State University Master of Science Thesis Reports" (2023). All Graduate Theses and Dissertations, Spring 1920 to Summer 2023. 8815.
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .