'Including studies with zero events in both arms in meta-analysis of binary outcomes
I am doing meta-analyses using meta. I aim to do meta-analysis of a binary outcome, including trials with zero events in both arms. I use Mantel-Haenszel random-effects models, and I use the allstudies = TRUE function to include studies with zero events in both arms. However, I am not sure how these studies are included. Does the allstudies function use a continuty correction or how does it work?
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|