MR Dictionary

Robust MR method developed for a two-sample MR setting with summary-level data that identifies and removes invalid instrumental variables (IVs) based on Lasso regression.

Method uses Lasso regression, which involves adding a penalty term to the causal effect estimator that shrinks the regression coefficient towards zero and forces coefficients of individual IVs to be zero. The shrinkage can thus be used to identify and remove the effects of invalid IVs. See also MR Robust and MR with penalized weights.


Other terms in 'Pleiotropy-robust two-sample MR methods':