Field note · May 20, 2025
Pattern: Counting your tests
Twenty segments at α = 0.05 gives you a one-in-two chance of a false finding. Correct for it, or at minimum say how many you ran.
The shape: Holm–Bonferroni over the family of tests you actually looked at. — that is Counting your tests, and it comes up more than it should.
Twenty segments at α = 0.05 gives you a one-in-two chance of a false finding. Correct for it, or at minimum say how many you ran.
What makes it a pattern rather than a tip is that the wrong version is the one you write naturally. It reads correctly, it runs, and it returns something. The failure is in the result, not in the execution — which means the only defence is recognising the shape before you are in it.
Two datasets on this site have the shape built in: clinical-trial and ab-test-checkout. Both are small enough to run the broken version, see the number, then run the corrected one and see it change.
It lives under measuring because the arithmetic is fine and the interpretation is not, which is the harder failure to catch — nothing about the output looks wrong.
The long-form treatment is in the course (tests-you-actually-need, reading-a-result); the pattern page is the version to read at 4pm with a query open.
If you have a better formulation of this one, the repository takes issues. Several entries there are sharper than what we started with because someone pushed back.