A method developed for two-sample MR settings that combines Wald ratio (or ratio estimates) together into a meta-regression (with an intercept and slope parameter) to estimate the causal effect adjusted for any directional pleiotropy.
All single nucleotide polymorphisms (SNPs) being used as instrumental variables (IVs) can be invalid due to pleiotropy (specifically, horizontal pleiotropy) as long as the pleiotropy satisfies the Instrument Strength Independent of Direct Effect – InSIDE - assumption. This method can be implemented in a Bayesian framework but standard implementation requires the associations between the IVs and exposure to be orientated in a positive direction. The radial MR formulation avoids this step. The intercept of a MR-Egger regression provides an indication of horizontal pleiotropy when it is not null. Similar to the inverse variance weighted (IVW) method, the NO Measurement Error (NOME) assumption (i.e., that the association between the SNP and exposure is known, rather than estimated, with no measurement error), still holds and, if violated, there may be weak instrument bias. This can be tested with the I-squared statistic with the MR-Egger method.
References
- Burgess S, Bowden J, Fall T, Ingelsson E, Thompson SG. Sensitivity Analyses for Robust Causal Inference from Mendelian Randomization Analyses with Multiple Genetic Variants. Epidemiology 2017; 28: 30-42.
- Bowden J, Davey Smith G, Burgess S. Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression. International Journal of Epidemiology 2015; 44: 512-525.
- Bowden J, Spiller W, Del Greco M F, et al. Improving the visualization, interpretation and analysis of two- sample summary data Mendelian randomization via the Radial plot and Radial regression. International Journal of Epidemiology 2018; 47: 1264-1278.
- Schmidt AF, Dudbridge F. Mendelian randomization with Egger pleiotropy correction and weakly informative Bayesian priors. International Journal of Epidemiology 2018; 47: 1217-1228.
- Bowden J, Del Greco MF, Minelli C, Davey Smith G, Sheehan NA, Thompson JR. Assessing the suitability of summary data for two-sample Mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic. Int J Epidemiol 2016: 45; 1961-1974.
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 Mixture (MRMix)
- MR using Robust regression (MR Robust)
- MR with penalized weights
- MR with regularization
- MR-Clust
- MR-Link
- MR-Path
- Multivariable MR (MVMR) and extensions
- Welch-weighted Egger regression (WWER)