MR method for two-sample MR settings that accounts for correlated and uncorrelated horizontal pleiotropy when estimating the causal effect of an exposure on an outcome.
Correlated pleiotropy is most likely to arise when genetic variants being used as an instrumental variable (IV) influence both the exposure and outcome through a heritable shared factor (e.g., a confounder of the exposure and outcome association). Uncorrelated pleiotropy occurs when the genetic variants being used as an IV influences the outcome in a manner that is independent from the exposure (i.e., what is traditionally depicted as horizontal pleiotropy). Both correlated and uncorrelated pleiotropy are sources of bias in MR analyses due to violations of the exclusion restriction criteria. MR-CAUSE assumes that genetic variants influence the exposure either directly or via a confounder of the exposure and outcome (where there exists no direct influence of the genetic variant on the exposure). In the presence of a causal effect of an exposure on an outcome, the effect estimates of the association between the IV and exposure and between the IV and the outcome are correlated for all genetic variants with a non-zero effect on the exposure. For a subset of genetic variants with no direct effect on the exposure, a shared factor (i.e., confounder of the exposure and outcome) induces this correlation. MR-CAUSE uses this distinction to differentiate causal effects from correlated pleiotropy.
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
- 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 Mixture (MRMix)
- 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)