## Direct evidence 1. The size of the effect is not (plausibly) attributable to confounding. 2. There is appropriate temporal or spatial proximity between cause and effect. 3. The effect increases and decreases in response to the dose. ## Mechanistic evidence 4. There is a plausible mechanism of action. ## Parallel evidence 5. Coherence: The effect fits with what is known already. 6. Consistency: The effect is found when the study is replicated. 7. Similarity: The effect is found in similar studies. At least 5 of the above points and at least one in each evidence group should hold true before considering that causality is at play. Source: Jeremy Howick, [The Evolution of Evidence Hierarchies](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2677430/table/tbl1/); Modified from Bradford Hill.