Evaluating Student Creativity, Depth and Multivariate Visualizations of Data Analysis projects based on R Syntax and Packages
Programming has become an essential component of introductory statistics, as students use R to explore general concepts. Currently, there are two methods of teaching R for beginning statisticians, but not much literature on how they affect student comprehension and analysis. We analyzed 205 final projects written using the two syntaxes for an introductory statistics course at Duke University from the 2013-2016 academic years, creating a variety of indicator variables to measure their creativity, depth and the complexity of multivariate visualizations. Student projects using the tidyverse syntax were found to score significantly higher on all three metrics, suggesting instructors should employ the tidyverse when teaching beginning statistics. Based on these results from the retrospective study, we created resources designed for future use in statistical instruction.
Keywords: Introductory statistics, Education, Tidyverse, Creativity, Depth, Multivariate visualizations, Retrospective study
I thank my advisor, Dr. Mine Çetinkaya-Rundel for her immense dedication and support in supervising this project. I could not have done this without her, let alone obtain a legitimate dataset to perform a comparative analysis. I also thank Dr. Victoria Ellison for her essential advice, and the Department of Statistical Science for providing me with the tools to complete this project. Most of all, I thank my family and friends for their love and belief in me for the past 21 years.
I dedicate my thesis to my past students for whom I have been a teaching assistant for their enthusiasm that gave me the motivation to complete this thesis.
This project was approved by the Duke University Institutional Review Board, 2019-0130