Per-Protocol analyses produced larger treatment effect sizes than intention to treat: a meta-epidemiological study

• Published in: Journal of clinical epidemiology Vol. 138; pp. 12 - 21
• Main Authors: Mostazir, Mohammod, Taylor, Gordon, Henley, William Edward, Watkins, Edward Robert, Taylor, Rod S
• Format: Journal Article
• Language: English
• Published: Elmsford Elsevier Inc 01.10.2021; Elsevier Limited
• Subjects: Bias; Complier average causal effect (CACE); Drug dosages; Epidemiology; Estimates; Hypotheses; Intention-to-treat; Internal Medicine; Intervention; Meta-analysis; Meta-epidemiology; Non-adherence; Per-protocol; Randomised controlled trial; Randomization; Sensitivity analysis; Complier average causal effect (CACE); Meta-epidemiology; Per-protocol; Non-adherence; Randomised controlled trial; Intention-to-treat; per-protocol; randomised controlled trial; intention-to-treat; complier average causal effect (CACE); meta-epidemiology

To undertake meta-analysis and compare treatment effects estimated by the intention-to-treat (ITT) method and per-protocol (PP) method in randomized controlled trials (RCTs). PP excludes trial participants who are non-adherent to trial protocol in terms of eligibility, interventions, or outcome asse...