Debiased inverse-variance weighted estimator in two-sample summary-data Mendelian randomization

Mendelian randomization (MR) has become a popular approach to study the effect of modifiable exposure on an outcome by using genetic variants as instrumental variables. A challenge in MR is that each variant explains relatively small proportion variance and there are many such variants, setting known weak instruments. To this end, we provide theoretical characterization statistical properties two estimators MR: inverse-variance weighted (IVW) estimator IVW with screened instruments independent selection dataset, under We then propose debiased estimator, simple modification robust does not require screening. Additionally, present instrument methods improve efficiency new when dataset available. An extension handle balanced horizontal pleiotropy also discussed. conclude demonstrating our results simulated real datasets.