In this meta-analysis on the use of stem cell and platelet enriched plasma to treat soft tissue injuries in horses appears to use the same control group in 5 studies. I believe in looking at the studies that it is the same historical control group. Is this problematic?
Yes, it would create a unit of analysis error. The studies with 46 control participants do look suspicious but one would have to look at the individual studies to know for sure.
I received this response from Stephen Senn on Twitter> Using the same controls more than once is not allowed unless you take account of the induced covariance between contrasts that are now not independent . That is to say, standard meta-analysis approaches will be wrong.mphasized text
2 Likes