Hill’s criteria are useful for evaluating whether an (environmental) association is likely to be causal. Most statistical associations will not be causal.
- What is the degree to which the exposure is associated with the outcome ?
- Has the association been repeatedly observed by different persons, in different places, circumstances, and times ?
- Is the observed association limited to the exposure and outcome?
- Does a particular intervention lead to disease or do early stages of disease lead to those with the disease undertaking a particular confounding intervention
- Is there a dose–response relationship between the exposure and outcome?
- Is there a physiological basis for the observed association?
- Does the “cause-and-effect interpretation” of the association “seriously conflict” with “generally known facts about the natural history and biology of the disease”?
- Is the frequency of associated events [outcomes] affected by actions to prevent the exposure?
- Does an exposure with a similar action (physiologically) cause the outcome?
Adapted from Hill
- ↑ Hill AB. The environment and disease: association or causation? Proc R Soc Med 1965;58:295-300