Bradford-Hill’s criteria for causation

Sir Austin Bradford-Hill. Image available in the public domain.

Establishing causation between variables is a fundamental pursuit in the realm of scientific understanding. Before modern quantitative and more formal methods arrived, Sir Austin Bradford-Hill proposed a set of heuristics or criteria. These offer a simple-to-understand approach to assess whether a putative connection between an exposure (or treatment) and an outcome might be causally related.

The Bradford-Hill criteria

1. Strength of Association: A strong association between the exposure and the outcome is more likely to be causal. This means that a large effect size or a substantial increase in risk should be observed.
2. Consistency: The association should be consistently observed in different studies, populations, and settings.
3. Specificity: The exposure should be specifically linked to the outcome, rather than being associated with multiple outcomes.
4. Temporal precedence: The exposure should precede the development of the outcome in time. In other words, the cause should come before the effect.
5. Dose-Response Relationship: There should be a dose-response relationship, meaning that increasing levels of exposure are associated with a corresponding increase in the risk of the outcome.
6. Plausibility: The proposed causal relationship should be biologically plausible based on existing knowledge and understanding of the mechanisms involved.
7. Coherence: The causal relationship should be consistent with what is known about the natural history of the disease and other established facts.
8. Experimentation: Experimental evidence, such as intervention studies or randomized controlled trials, can provide stronger evidence for causality.
9. Analogy: Similarities with other established causal relationships can strengthen the argument for a new causal relationship.

Evaluation

As our methods and grasp of causality have grown, it has become clear that while Bradford-Hill’s Criteria were a good start, they are not the whole story. Nowadays, we have a better and more quantitative toolkit to understand cause and effect.

Our current toolkit focuses on things like path diagrams (aka Directed Acyclic Graphs), structural causal models, potential outcomes, the do-operator, interventions, and counterfactuals. These are all very fun things that are worth learning about, but are less immediately accessible than Bradford-Hill’s verbal criteria.

Anyone with a passing interest in understanding how the world works would benefit from knowing about Bradford-Hill’s criteria. But their primary utility these days is in better understanding the historical development of causal thinking, and perhaps engaging with laypeople.

References

Bradford-Hill, A. (1965). The Environment and Disease: Association or Causation? Proceedings of the Royal Society of Medicine. 58(5): 295–300. doi:10.1177/003591576505800503