SSA SCV Tutorial: Creating data plots for effective decisionmaking using statistical inference with R
Website: https://StatSocAus.github.io/tutorial_effective_data_plots
This is for statisticians and data science practitioners who are interested in improving their data visualisation skills.
Presenter: Dianne Cook is Professor of Business Analytics at Monash University in Melbourne, Australia. She is a world leader in data visualisation, especially the visualisation of highdimensional data using tours with lowdimensional projections, and projection pursuit. She is currently focusing on bridging the gap between exploratory graphics and statistical inference. Di is a Fellow of the American Statistical Association, past editor of the Journal of Computational and Graphical Statistics, current editor of the R Journal, elected Ordinary Member of the R Foundation, and elected member of the International Statistical Institute.
Structure of tutorial
 Review of making effective plots using ggplot2’s grammar of graphics:
 Organising your data to enable mapping variables to graphical elements,
 Common plot descriptions as scripts,
 Do’s and don’ts following cognitive perception principles.
 Making decisions and inferential statements based on data plots
 What is your plot testing? Determining the hypothesis based on the type of plot.
 Creating null samples to build lineups for comparison and testing.
 Conducting a lineup test using your friends to determine whether what you see is real or spurious, and to determine the best design for your plot.
Background: Participants should have a good working knowledge of R, and tidy verse, and some experience with ggplot2. Familiarity with the material in R4DS (https://r4ds.hadley.nz) is helpful.
Course Schedule
time  topic 

1:001:15  Why, philosophy and benefits 
1:151:35  Organising data to map variables to plots 
1:352:05  Making a variety of plots 
2:052:30  Do but don’t, and cognitive principles 
2:303:00  BREAK 
3:003:20  What is your plot testing? 
3:203:35  Creating null samples 
3:354:00  Conducting a lineup test 
4:004:30  Testing for best plot design 
Getting started
 You should have a reasonably up to date version of R and R Studio, eg RStudio RStudio 2023.06.2 +561 and R version 4.3.1 (20230616). Install the following packages, and their dependencies.
install.packages(c("ggplot2", "tidyr", "dplyr", "readr", "stringr", "nullabor", "colorspace", "palmerpenguins", "broom", "ggbeeswarm"), dependencies=c("Depends", "Imports"))

Download the Zip file of materials to your laptop, and unzip it.

Open your RStudio be clicking on
tutorial.Rproj
.
GitHub repo with all materials is https://statsocaus.github.io/tutorial_effective_data_plots/.