Statistical methods can be improved within Cochrane pregnancy and childbirth reviews

Ref ID 600
First Author R. D. Riley
Journal JOURNAL OF CLINICAL EPIDEMIOLOGY
Year Of Publishing 2011
URL https://www.jclinepi.com/article/S0895-4356(10)00284-2/fulltext
Keywords • Cochrane
• Expertise
• Gynaecology
• Statistical
• Publication bias
• Heterogeneity
• Inference
Problem(s) • Inadequate analysis of heterogeneity
• Poor consideration of publication bias
• Lack of statistical expertise in handling of quantitative data
• Incorrect interpretation or statistical inference error from meta-analysis
Article Type Empirical
Article Subtype Cross-sectional survey/Methodological systematic review
First Author Country United Kingdom
Aim To assess statistical methods within systematic reviews of the Cochrane Pregnancy and Childbirth Group that contained at least ten included studies
Level of Investigation Descriptive
Summary of Findings Of the 44 reviews that reported one or more random effects meta-analyses, none correctly interpreted its pooled result. 91% of reviews did not assess publication bias. 65% of reviews with substantial heterogeneity did not explore the causes of the heterogeneity.
Number of systematic reviews included 75
Number of eligible systematic reviews assessed 365
Treatment impacted No
Treatment impacted description
Interpretation impacted Not Applicable
Interpretation impacted description