mr.simss: Mendelian Randomisation (MR) method that combats Winner's Curse using a simulated sample splitting approach

A package designed to provide users with a method, namely MR-SimSS, which uses simulated sample splitting in order to alleviate Winner's Curse bias in MR causal effect estimates. This approach also takes into account sample overlap between the exposure and outcome genome-wide association studies. It uses summary statistics from genome-wide association studies and works in combination with existing MR methods, such as IVW and MR-RAPS.

Details

Full documentation available here: https://amandaforde.github.io/mr.simss/