MR method developed for two-sample MR settings with summary-level data that generates robust and unbiased causal effect estimates in the presence of directional horizontal pleiotropy using a spike-detection algorithm under a normal-mixture model.

MRMix uses a normal-mixture model where distinct mixture components are incorporated to allow genetic correlations to arise from both causal and non-causal relationships. The causal effect is estimated through the maximization of the probability concentrations of residuals defined by the total effect of genetic variants being used as instrumental variables (IVs) on one trait (e.g., the exposure) after subtracting the indirect effects through another trait (e.g., the outcome). The method is robust to bias from a large number of invalid IVs and produces precise causal estimates.

## References

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

- Bayes MR
- Bayesian implementation of the MR-Egger Estimator (BMRE)
- Bayesian multi-instrument Mendelian randomization (MIMR)
- Bayesian network analysis
- Causal Analysis Using Summary Effect estimates (MR-CAUSE)
- Contamination mixture models
- Generalized Summary MR (GSMR)
- Genetic Instrumental Variable (GIV)
- Hierarchical joint Analysis of Marginal summary statistics (hJAM)
- Inverse variance weighted (IVW) random effects model
- Iterative Mendelian Randomization and Pleiotropy (IMRP)
- Leave-one-out analysis
- Median-based estimate
- Mode-based estimate
- MR accounting for Correlated and Idiosyncratic Pleiotropy (MRCIP)
- MR accounting for Linkage Disequilibrium and Pleiotropy (MR-LDP)
- MR Lasso
- MR using Robust regression (MR Robust)
- MR with penalized weights
- MR with regularization
- MR-Clust
- MR-Egger regression and extensions
- MR-Link
- MR-Path
- Multivariable MR (MVMR) and extensions
- Welch-weighted Egger regression (WWER)