Evidence-appraisal glossary
Equivalence trial
An equivalence trial is designed to show that two treatments differ by no more than a small, pre-specified amount (the equivalence margin) in either direction. Instead of proving one is better, it aims to demonstrate the two are close enough to be considered practically interchangeable.
Also called: equivalence study, therapeutic equivalence trial, equivalence design.
What it is
Most trials test for a difference. An equivalence trial flips that goal: it asks whether two treatments are similar enough to be treated as interchangeable. Researchers pre-specify an equivalence margin (often written as plus or minus delta) that marks the largest difference still considered clinically unimportant. Equivalence is declared only when the whole confidence interval for the difference falls inside that margin on both sides.
How to use it when reading a study
- Find the margin, and check it was set in advance. A margin chosen after seeing data, or set too wide, can manufacture "equivalence."
- Look at the confidence interval, not just the p-value. The interval must sit entirely within the margins.
- Distinguish it from non-inferiority, which only guards one side (not meaningfully worse). Equivalence guards both.
- Beware underpowered trials: a small, noisy study fails to find a difference, but absence of evidence is not evidence of equivalence.
- Confirm assay sensitivity: the trial should be able to detect real differences, ideally with per-protocol and intention-to-treat analyses agreeing.
Read the full Reading the Evidence blog.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.