Book of Apps for Statistics Teaching

The apps in this collection are the work of undergraduate students majoring in Statistics at Penn State University. These students took part in the BOAST (Book of Apps for Statistics Teaching) program in 2017-2023. The program included either a DataCamp course on Shiny (2018, 2019) or a full day workshop at the U.S. Conference On Teaching Statistics on Developing R Shiny Applications to Enhance Teaching and Learning presented by Justin Post and Herle McGowan from North Carolina State University (2017). This was followed by a full-time summer research experience developing the apps in this collection throughout the months of June and July. Finally, the BOAST students take part in a one-credit research class in Fall semester to showcase their work to statistics instructors, prepare a survey and IRB application to get student feedback in a human subjects research setting, and then formally test their apps in a live class. Besides gaining expertise in R and R Shiny, the students gained a deeper understanding of selected statistical concepts and learned crucial skills in the team-based reproducible development of software (e.g. though the use of the GitHub platform). This book is laid out in thirteen chapters with four at the introductory level covering topics in Data Gathering, Data Description, Basic Probability, and Statistical Inference, eight chapters at the upper division level covering Probability, Regression, ANOVA, Time Series, Sampling, Categorical Data, Data Science, and Stochastic Processes, and one chapter devoted to statistical topics in Biology.

Table of Contents

• Chapter 1: Data Gathering
  • Bias and Reliability
  • Mouse Experiment on Random Assignment
  • Survey Bias
  • Variable Types Matching Game
• Chapter 2: Data Description
  • Correlation Guessing
  • Descriptive Statistics
  • Effect of Outliers
  • Location and Variation
  • Measures of Association
  • Regression Lines
• Chapter 3: Basic Probability
  • Central Limit Theorem
  • Law of Large Numbers
  • Tree Diagrams
  • Venn Diagrams
• Chapter 4: Statistical Inference
  • Hypothesis Testing
  • Hypothesis Testing Game
  • Inference for Means
  • Inference for Proportions
  • Significance Testing Caveats
  • Simpsons Paradox
  • Testing and CI Relationship
  • Waiter Experiment
• Chapter 5: Probability
  • Bayes Theorem
  • Matching Distributions
  • Probability Applications
• Chapter 6: Regression
  • Regression Assumptions
  • Overfitting
  • QQ Plot
  • Variable Selection
  • Variance Inflation Factor
• Chapter 7: ANOVA
  • ANCOVA
  • ANOVA Models
  • Assumptions of ANOVA
  • Hasse Diagrams
  • One-Way ANOVA
• Chapter 8: Time Series
  • Time Series Decomposition
  • Time Series Models
• Chapter 9: Sampling
  • Sampling Methods
  • Weight Adjustment in Surveys
• Chapter 10: Categorical Data
  • Chi-Square Goodness of Fit Test
  • Chi-Square Independence Test
  • Logistic Regression
  • Odds Ratio
• Chapter 11: Data Science
  • Data Wrangling
  • Data Visualization App
  • Log Transformations
  • Training vs. Testing Dataset Proportions
• Chapter 12: Stochastic Processes
  • Homogeneous Poisson Process
  • Markov Chain Convergence
  • Nonhomogeneous Poisson Process
• Chapter 13: Biology
  • Life Table
  • Population Growth

Usage

The apps contained within this project are designed to be used as standalone activities or in conjunction with a lesson. Depending on your needs, you may want to clone the book as a whole or just a select chapter or app. The BOAST repository is a place for linking the individual projects within each chapter. As apps get updated, releases will trickle up to this level.

Apps can be run locally on your computer, self-hosted on a Shiny Server or RStudio Connect, or through managed hosting solutions like shinyapps.io. Note: There may be a cost associated with larger numbers of concurrent users.

RStudio Connect

As of RStudio Connect v1.7.6, apps can be deployed via Git Repository. This allows apps to self-update any time a commit is pushed to the tracked branch. Each app contains a manifest.json file to pull in the required dependencies. See Git Backed Content for more information.

Downloading

This book is separated by chapter into submodules, to download the entire book use the command:

git clone --recurse-submodules https://github.com/EducationShinyAppTeam/BOAST

Key People

• Program Co-Supervisors and Principal Mentors: Dennis Pearl (2017-2023) (dkp13@psu.edu) and Neil Hatfield (2019 - 2023)
• Faculty Mentors: Jacopo Di Iorio (2022), Matthew Beckman (2017 - 2021), and Priyangi Bulathsinhala (2017)
• Maintainers: Neil Hatfield (Past Maintainers: Bob Carey)
• 2023 BOAST Students: Sean Burke, Rob Chappell, Aisiri Cherrimane Narendra, Luqi Jiao Emanuele, Taryn McHugh
• 2022 BOAST Students: Jing Fu, Junjie He, Nurul Syafiqah Hamdi, Peter Phillips, Wanyi Su, Phichchaya Sutaporn, Xinyue Tang, Stuart Vas, Hongyi Xia, Yijun Yao
• 2021 BOAST Students: Ahmed Al Ali , Lydia Bednarczyk, Jiayue He, Paridhi Khandelwal, Kallien Peritz, Adam Poleski, Shravani Samala, Qiaojuan (Tina) Tu, Yudan Zhang, Xigang Zhang (2021 Peer Mentor)
• 2020 BOAST Students: Leah Hunt, Ethan Wright, Hogeun Choi, Chenese Gray, Dae Hoon Gwak, Zhuolin Luo, Gonghao Liu, Zeyuan Wang, Jiawei Wu, Xigang Zhang, Xuefei Wang, and Shunqi Zhang (2020 Peer Mentor)
• 2019 BOAST Students: Oluwafunke Alliyu (2019 Website Coordinator), Yiyun Gong, Sean Klavans, Yuqing Lei, Shubo Sun, Jingjun Wang, Ruisi Wang, Yiyang Wang, Zhiruo Wang, Yutong Wu, and Shunqi Zhang
• 2018 BOAST Students: Jiajun Gao, Stephen Li, Thomas Mclntyre, Samuel Messer, Angela Ting, Ryan J Voyack, Luxin Wang, Zhiliang Zhang, Yinqi Zhang, Yubaihe Zhou (2018 website coordinator)
• 2017 BOAST Students: Alex Chen, Qichao Chen, Jinglin Feng, Zibin Gao, Sitong Liu, Ryan Manigly-Haney, David Robinson, Yingjie Wang (2018 peer mentor), Caihui Xiao, Yuxin Zhang (2017 website coordinator)

Contributing

Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.

Disclaimer

Because of time constraints, these apps have not yet been thoroughly tested on multiple platforms and by large groups of users. Please post bugs to issues and suggestions for improvement to Dennis Pearl (dkp13@psu.edu). These apps are best optimized for Firefox / Chromium-based browsers.