paperKB
coga / coga-kb
Help
Sign in

Chunk #43 — SIMULATION STUDY — Causal relationships between the risk factors

Source
Extending the MR-Egger method for multivariable Mendelian randomization to correct for both measured and unmeasured pleiotropy.
Embedded
yes

Text

We performed additional simulations to investigate the behaviour of the multivariable MR‐Egger method when X 2 is causally dependent on X 1, and the causal effect of X 1 on X 2 is γ (Figure 3). The total causal effect of X 1 on Y is θ 1+γ θ 2, consisting of the direct effect (θ 1) and the indirect effect via X 2(γ θ 2). See the Web Appendix for more details on the data generating model.