Scatter plot encodes values as position of points on two quantitative axes. John Herschel plotted orbits; Galton’s 1880s regressions made the form famous.
In reports, ads and assignments it fits correlation, outliers and clusters in two measures. Skip it when one axis is not quantitative, or time is the real story.
Principles
- Encoding — Scatter plot encodes position of points on two quantitative axes.
- History — John Herschel plotted orbits; Galton’s 1880s regressions made the form famous
- Fit — correlation, outliers and clusters in two measures
- Shared baseline — The eye compares length and position more accurately than area.
- Audience — PowerPoint, Excel or Google Sheets and Meta, Google and retail print share the same geometry.
Misconceptions
- Pretty equals true — Decoration rarely persuades; it slows reading.
- 3-D helps — Perspective distortion wrecks comparison. Keep it flat.
- More series is richer — Do not stack stories. One Scatter plot, one claim.
- Default palette is fine — Rainbow defaults fail color-blind viewers and grey print. Change Excel or Google Sheets defaults.
Why it matters
- Work — Work: correlation, outliers and clusters in two measures. Readable in four minutes in PowerPoint.
- Ads — Ads: one number and one shape speak first in Meta, Google and retail print.
- School — School: for lab reports and poster boards, pick the form that answers the rubric.
- Craft — Craft: honour position of points on two quantitative axes and decoration falls away.
Scatter plot: honour position of points on two quantitative axes, and switch when one axis is not quantitative, or time is the real story.