3 · Describing data
Distributions, summaries, correlation
Before fitting anything, look at the data. This topic covers summarising and plotting numerical and categorical variables, and measuring how two variables move together — along with the ways correlation can mislead you.
Slides
| Deck | Covers |
|---|---|
| 🖥 Exploring numerical data | Distributions, summaries, histograms, boxplots, scatterplots |
| 🖥 Correlation | Correlation types, interpreting strength, and where correlation misleads |
Exercises
| Exercise | What you practise |
|---|---|
| 📋 AE03-02 Plastic waste | Exploring the distribution of plastic waste per capita across countries |
| 📋 AE03-02 — solutions | Worked solutions to the above |
| 📋 AE03-03 Correlation | Computing correlations and reading their strength |
| 📋 AE03-04 Categorical data | Homework: visualising categorical variables |
📦 Bundles: ae03-data-wrangling · ae03-data-wrangling-hw
Exploring numerical data
Read
Practise
- Deriving information with dplyr
- Visualising numerical data (interactive, slow to load)
- Summarising data (interactive, slow to load)
- Histograms · Boxplots and counts · Scatterplots
Watch (optional)
Exploring categorical data
Read
Practise
- Visualising categorical data (interactive, slow to load)
Watch (optional)
- 📺 Visualising categorical data: video + slides
- 📺 Webinar: Tidyverse visualization manipulation basics
Correlation
Read
Practise