Evidence-appraisal glossary
Per-protocol analysis
A per-protocol analysis includes only participants who followed the trial's rules closely, completing the assigned treatment without major deviations. It estimates the effect under ideal adherence, but by dropping non-compliers it can break randomization's balance and overstate benefit. It is usually read alongside intention-to-treat.
Also called: per protocol, PP analysis, on-treatment analysis.
A per-protocol analysis restricts the comparison to participants who adhered to the study protocol: they took the assigned treatment as directed, met eligibility criteria, and had no major deviations. The aim is to estimate the effect of the treatment when it is actually taken as intended, sometimes called efficacy under ideal conditions. The trade-off is that excluding non-adherent participants can undo the balance that randomization created, because people who complete treatment often differ systematically from those who drop out, which tends to make the treatment look better than it is. When reading a study, treat a per-protocol result as supportive rather than primary, and compare it with the intention-to-treat estimate; agreement between the two strengthens confidence, while a large gap is a warning. Example: if a diet trial reports strong results only among people who stuck to the diet, the per-protocol figure flatters the intervention. Ask how compliers were defined and how many were excluded.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.