Interpreting and Communicating Statistical Results with R: A Short Course

By the end of this class, you’ll be well-equipped to not only make sense of complex statistical results but also to communicate them in a compelling and engaging manner, ensuring that your research or work has a lasting impact. With a comprehensive understanding of the distinctions between various statistical concepts and the ability to apply an advanced toolkit in R, you’ll be prepared to tackle statistical challenges with confidence.

The course content includes:

• • Clarifying distinctions between statistical concepts such as predictions, contrasts, marginal means, marginal effects, odds ratios, and risk ratios.
  • Introducing a powerful toolkit in R to compute and report the most appropriate quantities of interest for your use case.
  • Generating plots and tables to illustrate your findings.
  • Creating reproducible reports and slideshows for stakeholders.

You will also be introduced to several useful R packages, including:

• • marginaleffects: https://vincentarelbundock.github.io/marginaleffects
  • modelsummary: https://vincentarelbundock.github.io/modelsummary/
  • tinytable: https://vincentarelbundock.github.io/tinytable/

This course is for anyone who wants to leverage the power of statistical models to deliver clear, compelling insights. If you are a data analyst, researcher, statistician, or data-driven professional who often needs to interpret complex statistical models and communicate findings in an intuitive, comprehensible manner, this course is for you.

While the course is designed to be broadly accessible, the instructor will assume that you have a working knowledge of R programming (at the level of our Introduction to R for Data Analysis, R for SPSS Users, or R for Stata Users courses) and linear regression models. A basic understanding of generalized linear models would also help you get the most out of the course, but it is not essential.

To participate in the hands-on exercises, you are strongly encouraged to use a computer with the most recent version of R installed, together with the tidyverse, marginaleffects, modelsummary, and tinytable libraries. You are also encouraged to download and install RStudio, a front-end for R that makes it easier to work with. This software is free and available for Windows, Mac, and Linux platforms.

Basic familiarity with R is highly desirable, but even novice R coders should be able to follow the presentation and do the exercises.

If you’d like to take this course but are concerned that you don’t know enough R, there are excellent on-line resources for learning the basics. Here are our recommendations.

1. The programming environment

1. • R
   • Rstudio
   • Quarto
   • R Libraries
     1. Modelling: MASS, mgcv, brms
     2. Interpretation: marginaleffects
     3. Communication: modelsummary, tinytable

2. Statistical building blocks

1. • Predictions
   • Comparisons
   • Slopes
   • Hypothesis and equivalence tests

3. Interpretation

1. • Using the marginaleffects package to compute quantities of interest

4. Communication

• • Automatically generating plots to communicate results:
    • marginaleffects
  • Automatically generating tables to summarize datasets and model results:
    • modelsummary
    • tinytable

“This course was fun! Students were encouraged to ask questions, and Vincent is an incredibly thoughtful, knowledgeable, and friendly instructor. It was a delight to learn from him. His teaching style is very clear, and he adapts content to students’ needs and interests. The smaller group size made the class feel more intimate, which may have also facilitated engagement. I enjoyed the interactive exercises and anticipate revisiting the many resources that Vincent shared regularly in future work. Thanks so much!”
  Kirsten Helgeson, Prevention Research Center

“Vincent Arel-Bundock is an outstanding teacher! He is warm and human, modest, knowledgeable, and most importantly, he genuinely cares about the learners. In addition, the “marginaleffects” package is a game-changer! This package is influencing both my research and teaching like few online courses I have taken before.”
  Ofer Engel, UMCG 

“Thank you for organizing this amazing workshop. I have attended a few statistics workshops so far, and this one was one of the best (or maybe the best) ones I have ever taken. Vincent is an amazing instructor and I hope I can attend his other courses, or one of the other interesting courses on your website in the future.”
  Omid Ghasemi, Institute for Climate Risk and Response, University of New South Wales 

“This course was incredibly useful. Vincent was great about explaining concepts before jumping into their application. We were given plenty of exercises and code to apply what we learned and reference in the future. I wish I could have taken this course years ago. This was the best way to spend my NSF postdoc professional development funds. I would highly recommend this course to literally anyone who uses R to interpret or communicate results.”
  Rebecca Brittain, Rutgers University 

“Vincent is an excellent teacher. The content was very relevant and will help me simplify my work. This was one of the best workshops I’ve ever taken! I will definitely be on the lookout for anything else Vincent teaches.”
  Taylor Heffer, Harvard University 

“I appreciated the ease and clarity that was provided while teaching the course.”
  Harshit Arora, University of Kentucky 

“I learned a lot in this course. There was very good overview and explanations. This was a great course!”
  Henrik Hein Lauridsen, University of Southern Denmark