Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 3 Statistical analysis method categorized by overall strategy among 26 IPD meta-analyses of binary outcomes

From: Systematic review of methods for individual patient data meta- analysis with binary outcomes

Analytic approach1 n/N (%)
One stage approach (n = 19)  
Ignored clustering by study Logistic regression 5/19 (26%)
Fixed effects Logistic regression 4/19 (21%)
Random effects Logistic regression 10/19 (52%)
Fixed study effect with random treatment effect2 1/10 (10%)
Random study effect with fixed treatment effect2 2/10 (20%)
Random study effect with random treatment effect2 2/10 (20%)
Unclear1 5/10 (50%)
Two stage approach (n = 6)  
Fixed effects Unspecified 2/6 (33%)
Cochrane-Mantel-Haenszel 1/6 (17%)
Random effects Der Simonian Laird 2/6 (33%)
Unspecified 1/6 (17%)
  1. 1It was unclear from one article [38] which approach was used.
  2. 2Among studies that used random effects logistic regression, where the intercepts and/or treatment effects allowed to vary across studies.