Now, the association of the genetic variants with the outcome can be decomposed into indirect effects via each of the risk factors and a residual direct effect αj′. Assuming there are 3 risk factors and all relationships are linear: (5)βYj=αj′+θ1βX1j+θ2βX2j+θ3βX3j, where θ k is the causal effect of the risk factor k on the outcome (Figure 2). We assume that the risk factors do not have causal effects on each other; we later relax this assumption and allow for causal effects between the risk factors.
