I'm trying to perform an IPD multivariate meta-analysis and, as suggested here https://onlinelibrary.wiley.com/doi/full/10.1002/jrsm.1129, I am using SUR to model the outcomes jointly. However, I have some missing observation in my dataset and when I perform the analysis I get this:
In systemfit(list(M1 = m1, M2 = m2), "SUR", data = Sn): the estimation of systems of equations with unequal numbers of observations has not been thoroughly tested yet
Any suggestions on how to deal with this?