Similar IVW (fixed effect) but approached using a maximum likelihood method where the genetic effects on the exposure and outcome are modelled directly as a bivariate normal distribution.
The method requires a term which represents the proportion of sample overlap between the exposure and outcome datasets. Requires an iterative estimating procedure that can occasionally fail to converge. This method is largely equivalent to IVW and is no longer commonly used.
- Burgess S, Dudbridge F, Thompson SG. Combining information on multiple instrumental variables in Mendelian randomization: comparison of allele score and summarized data methods. Statistics in medicine 2016;35:1880-1906.