I am trying to run an Individual Patient Metanalysis (IPD) in R. However, using a Random Intercept Model seems not to be appropriate since I only use 4 Trials.

In this article a stratified study intercept is proposed like this: enter image description here

In a random effects model I would have fitted the model like this:

lmer(outcome ~ treatment + baseline + (1 + treatment | trial), data = data)

Can anyone help me get my head around implementing the stratified intercept instead of the random-effects model? I understand that the idea is to fit a model for every trial and use the trial-specific intercept, but I don't understand how to get it all together in the end.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.