@petermacp @stephenjwild I can't help with R coding but, in STATA, I think I would use an IVhet model on double arcsine transformed data. The inputs would be the point estimate and bounds of confidence interval for each study (adjusted or not) https://t.c
1,741 followers
1,741 followers
RT @tomayates: Hi #statstwitter / #epitwitter If you are going to meta-analyse heterogeneous studies, is there a good reason NOT to use th…
1,741 followers
Hi #statstwitter / #epitwitter If you are going to meta-analyse heterogeneous studies, is there a good reason NOT to use the IVhet model? Seems intuitively very appealing but I don't see it being widely applied https://t.co/BmiqfdBDL9
1,741 followers
Meta-analysis friends, what do we think about IVhet model and Doi plots? IVhet better than RE if unexplained heterogenetity? https://t.co/BmiqfdBDL9 Doi plots better than funnel plots for spotting publication bias? https://t.co/eXOJz56KyI @KatharinaKr