Exploring treatment by covariate interactions using subgroup analysis and meta-regression in cochrane reviews: a review of recent practice

Ref ID 547
First Author S. Donegan
Journal PLOS ONE
Year Of Publishing 2015
URL https://pubmed.ncbi.nlm.nih.gov/26029923/
Keywords • Statistical
• Cochrane
• General medical
• Pre-specification
• Subgroup
• Multiplicity
Problem(s) • Multiplicity of outcomes and lack of pre-specification for outcome reporting
• Unplanned or unjustified subgroup or sensitivity analyses
Article Type Empirical
Article Subtype Cross-sectional survey/Methodological systematic review
First Author Country United Kingdom
Aim To assess how well interaction analyses were designed, applied, interpreted, and reported for the most recent review from each Cochrane review group in the Cochrane Database of Systematic Reviews in 2013
Level of Investigation Descriptive
Summary of Findings The type of analysis planned and the type subsequently applied (e.g., sensitivity or subgroup analysis) was discrepant in 46% of reviews. No review reported how or why each covariate had been chosen; 42% of reviews did state each covariate a priori in the protocol but no review identified each post-hoc covariate as such.
Number of systematic reviews included 52
Number of eligible systematic reviews assessed 52
Treatment impacted No
Treatment impacted description
Interpretation impacted Not Applicable
Interpretation impacted description