Egger
Resources
Code (Language: R) Website Paper (Pub Date: 2015-04-01)
Other URLS: https://cran.r-project.org/web/packages/MendelianRandomization/index.html
Method Contact: Jack Bowden ( J.Bowden2@exeter.ac.uk)
Entry Contact: Gibran Hemani ( g.hemani@bristol.ac.uk)
Context
Analysis Type: UVMR MVMR Network MR Bi-Directional MR Non-Linear
Input Data Types: Ind/Ind Ind/SS SS/Ind SS/SSfamily
Exposure Trait Types: Quantitative Binary Time to event
Outcome Trait Types: Quantitative Binary Time to event
Assumptions and Sources of Bias
| Source of Bias | Addressed |
|---|---|
| Weak instruments | ✗ |
| Winner’s curse | ✗ |
| Sample overlap | ✗ |
| Uncorrelated horizontal pleiotropy | ✓ |
| Correlated horizontal pleiotropy | ✗ |
| Ancestry differences in samples | ✗ |
| Residual confounding in GWAS | ✗ |
| Cross-trait assortative mating | ✗ |
| Index-event/conditioning on heritable trait | ✗ |
Description
Egger regression, a tool to detect small study bias in meta-analysis, can be adapted to test for bias from pleiotropy, and the slope coefficient from Egger regression provides an estimate of the causal effect. Under the assumption that the association of each genetic variant with the exposure is independent of the pleiotropic effect of the variant (not via the exposure), Egger’s test gives a valid test of the null causal hypothesis and a consistent causal effect estimate even when all the genetic variants are invalid instrumental variables.