MR Dictionary

The traditional definition of a confounder is that: i) It is associated with the exposure; ii) It is associated with the outcome conditional upon the exposure; iii) It is not on the causal pathway between the exposure and outcome. However, because this set of rules does not generalize to complex modelling structures, the modern interpretation uses Pearl's directional-separation rules. In this context, the modern definition of confounding is the existence of an open “backdoor pathway” between the exposure and outcome - where one or more characteristics influence the risk factor and outcome of interest and generate a spurious (confounded) association between risk factor and outcome. Confounding can generate a positive or negative association when there is no causal effect of risk factor on outcome and can exaggerate or attenuate a true causal effect. 

Associations of genetic variants with outcomes are generally less prone than associations of non-genetic characteristics to confounding by many socio-demographic, lifestyle and clinical characteristics from across the lifecourse. The independence assumption states that IVs are not associated with confounders of the risk factor-outcome association. In MR studies, demonstrating that genetic IVs are not related to observed risk factor-outcome confounders is important (though we cannot show they are not related to unobserved confounders). In two-sample MR with summary (aggregate) data, it may not be possible to explore associations with observed risk factor-outcome confounders in the outcome sample (sample 2). However, summary-level data from GWAS for any known or hypothesised confounders may be available and if so these should be used to explore whether there are associations with the risk factor-outcome confounders. 


Other terms in 'Sources of bias and limitations in MR':