Inadvertent P-hacking among trials and systematic reviews of the effect of progestogens in pregnancy? A systematic review and meta-analysis

Ref ID 201
First Author M. Prior
Journal BJOG: AN INTERNATIONAL JOURNAL OF OBSTETRICS & GYNAECOLOGY
Year Of Publishing 2017
URL https://obgyn.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/1471-0528.14506?download=true
Keywords • Subgroup
• Pre-specification
• Endocrinology
Problem(s) • Multiplicity of outcomes and lack of pre-specification for outcome reporting
Article Type Empirical
Article Subtype Meta-epidemiological analysis
First Author Country United Kingdom
Aim To compare the findings all progestogen trials and systematic reviews with those of trials with pre-registered primary outcomes which avoided selective outcome reporting.
Level of Investigation Analytical
Summary of Findings Nineteen of the included 29 meta-analyses concluded that progestogens were effective which the authors suggest was due to inadvertant p-hacking. When systematic reviews evaluated only the primary outcomes from pre-registered double-blind trials with analysis, progestogen agents in pregnancy were found to be ineffective (RR 1.00 (95% CI 0.94–1.07).
Number of systematic reviews included 29
Number of eligible systematic reviews assessed 2467
Treatment impacted Yes
Treatment impacted description Re-analysis using only the registered primary outcomes of the included trials.
Interpretation impacted Yes
Interpretation impacted description When systematic reviews evaluated only the primary outcomes from pre-registered double-blind trials with analysis, progestogen agents in pregnancy were found to be ineffective (RR 1.00 (95% CI 0.94–1.07).