Skip to content

Collider Bias

Definition
AI-generated

Collider bias arises when two variables both influence whether an individual is included in an analysis (or stratum), and conditioning on that inclusion opens a non-causal path between them, inducing spurious association or attenuating true effects.

Topics
Epidemiology
Related
Bias Case-Control Study Cohort

Why it matters in GWAS

Selection on disease severity, survival, biobank participation, or other post-outcome variables can distort genetic associations and downstream MR; within-family designs and careful phenotype definition partly mitigate selection-related collider structures.

Example usage

"Interpreting ICU survival GWAS required caution because conditioning on hospitalization can induce collider bias between genetics and acute severity."

Bias Case-Control Study Cohort Mendelian Randomization (MR) Participation Bias
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Munafò MR, et al. (2018). Collider scope: when selection bias can substantially influence observed associations. Int J Epidemiol.
  • Uffelmann E, et al. (2021). Genome-wide association studies. Nat Rev Methods Primers. https://doi.org/10.1038/s43586-021-00056-9
← Collapsing analysis Colocalization →

Last updated (UTC · Git history)