Advanced Graphics

Workshop on Information Visualization for Social Scientists

Author

Melanie Sauter

Welcome to this workshop on information visualization and advanced graphics in R.

Information visualization, the art of representing data in a way that it is easy to understand and to manipulate, can help us make sense of information and thus make it useful in our lives. There’s a huge need for data to be presented so that it is understood by experts and non-experts alike.

Some of the most famous information visualizations are maps of Underground/Subway systems. The geography above ground is very different to the way it is shown on the underground map. However, it enables pretty much anyone to quickly understand how to get from one point in the city to any other using the underground system.

Information visualization is designed to help us make sense out of data. It can be used to explore relationships between data, to confirm ideas we hold about data or to explain data in easy to digest manners. It may also be used, rightly or wrongly, to help persuade someone with data.

This workshop is an introduction to the principles and techniques for visualizing data. The course first and foremost is aimed at making researchers aware of “good” and “bad” visualizations. Participants learn the principles of how to visualize complex matters into readable charts and graphs.

Course Overview

Block	Topic	Pages
1	Design foundations	Colors, Fonts, Technicalities
2	Principles & chart choice	Data Visualization
3	ggplot2 in practice	Applied Examples, Tables
4	Communicating results	Annotation, Uncertainty, Accessibility
5	Beyond the static plot	Interactive Graphics, Exporting
—	Practice	Exercises, Solutions

Prerequisites

Basic familiarity with R (loading data, running functions) and some exposure to regression analysis. You do not need prior ggplot2 experience, but skim the ggplot2 introduction beforehand if it is new to you.

Setup: before the first session

Please bring a laptop with a recent R (≥ 4.3) and RStudio installed, and run the following once:

Code

install.packages(c(
  # core
  "ggplot2", "dplyr", "tidyr", "broom", "patchwork", "tidyverse",
  # colors & themes
  "viridis", "ggthemes", "colorspace", "cowplot", "scales",
  # annotation & uncertainty
  "ggrepel", "gghighlight", "ggdist", "ggeffects", "marginaleffects",
  # tables
  "gt", "modelsummary",
  # interactive
  "plotly", "ggiraph", "gganimate", "leaflet", "mapview",
  # spatial
  "sf", "terra", "rnaturalearth", "rnaturalearthdata", "osmdata",
  # export & data
  "ragg", "svglite", "scales", "gapminder"
))

# From GitHub (needs the 'remotes' package)
install.packages("remotes")
remotes::install_github("clauswilke/colorblindr")
remotes::install_github("vdeminstitute/vdemdata")

If sf or terra fail to install, see the sf installation notes for your operating system.

Questions?

Contact me at melanie.sauter@uni-mannheim.de.