← The Casebook

Case file

Clustering Illusion

Filed under
Not Enough Meaning

The charge

Clustering illusion is seeing meaningful streaks or clumps in data that are actually compatible with randomness.


How it operates

Human pattern detection is tuned to find structure quickly, and random processes naturally produce local clusters that feel non-random.

Logged incidents

  1. Incident 01

    A PM sees a burst of cancellations from one city and assumes a local competitor launched there.

  2. Incident 02

    A QA lead notices several bugs in one module over two days and concludes the architecture is uniquely broken.

  3. Incident 03

    An investor sees three founder departures in one month and reads it as proof of sector collapse.

What to watch for

Ask: Would this pattern still look impressive if I compared it with random data or a null model?

Recommended action

Use run charts or control charts and compare observed clusters to a random baseline before inferring a cause.

Known associates

Source of record

en.wikipedia.org

File your own case

Open the same case on your own draft.

Paste a memo, a research draft, or a strategy argument. It is scored against all 175 cards, and the strongest two or three risks come back with the evidence quoted and one practical next check.

Open a case on your draft →