Why add jitter

When many observations share the same or nearly the same value, a plain scatterplot can hide them by stacking points in the exact same spot.

Jitter solves that by adding a small horizontal offset while keeping the real measurement on the yy axis unchanged.

The result preserves the group structure but makes repeated values easier to count by eye.

When to use it

  • Comparing small grouped samples before building a box plot or violin plot.
  • Showing raw observations instead of only summary statistics.
  • Checking whether overlap is hiding clusters or repeated values.