Proceedings of the National Academy of Sciences · 14 August 2026 · From issue 22
Beyond “non-significant” results: Why and how to test for practical equivalence
A common science claim of "no difference" often just means the test was not sensitive enough.
Jakub Tomek, Aaron Caldwell et al.
A test result of "no significant difference" does not always mean two things are the same. It can also mean the study was too small or too noisy to find a real difference. This paper explains a method called equivalence testing that can tell these two cases apart. It also shares a free online calculator that lets scientists run this test without writing computer code.
Integrity screen: passed (3 checks) Checked 17 August 2026. Read the source
The plain-language reading of this paper is in the full issue, for subscribers.
Read the full issue