Visual Inference for the Classroom

In the classroom, we traditionally visualize inferential concepts related to inference using static graphics or interactive apps. For example, there is a long history of using apps to visualize sampling distributions. Recent developments in statistical graphics have created an opportunity to bring additional visualizations into the classroom to hone student understanding. Specifically, the lineup protocol (Buja et al., 2009) provides a framework for students see the difference between signal and noise. This protocol involves embedding a plot of observed data in field of null plots. This approach has proved valuable in visualizing randomization/permutation tests, diagnosing models, and even conducting valid inference when distributional assumptions break down.

In addition to writing about the use of visual inference in the classroom, I’ve also developed materials to facilitate its use.

Lineups Activity: Building Intuition for Two-Sample Inference

• Instructor guide

• Student handout

• R Markdown file with the code

• CreativeWriting.csv

Lineups Activity: Learning to Read Residual Plots

• Instructor guide

• Student handout

• R Markdown file with the code

• RailsTrails.csv

Tutorial using nullabor + ggplot2 to create lineups in R

Suite of Shiny apps for lineups in intro stats

• GitHub repository for Shiny apps

• Live Shiny apps

  • Detecting association: Two categorical variables
  • Detecting association: Quantitative vs. categorical
  • Exploring residual plots in SLR
  • Interpreting Q-Q plots

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.