 In this video, we are going to discuss Hill's criteria for association and causation. As we all know, association is the concurrence of two factors more than expected by chance. Whereas in causation, one factor plays a key role in the occurrence of the other factor. Sir Austin Bradford Hill, a British epidemiologist, proposed Hill's criteria of causation in 1965. The following are the considerations used to assess whether an observed association between an exposure and an outcome is likely to be causal. A higher strength of association or effect size between exposure and outcome suggests a higher likelihood of a causal relationship. Consistency or reproducibility observed in different studies, populations and circumstances. Specificity, as explained by exposure, is associated with a specific outcome and the outcome is not linked to multiple exposures. Temporality, as explained by the cause, must precede the effect in time. Biological gradient or dose-response relationship, meaning that higher levels of exposure are associated with a higher risk of the outcome. Plausibility, as explained by the proposed causal relationship, aligns with current biological knowledge and existing understanding of mechanisms. The proposed causal relationship is coherent or consistent with other known facts and does not conflict with established principles. Experimental evidence, such as randomized controlled trials, can provide stronger support for causation than observational studies alone. Analogy, as explained by similarities to other established causal relationships, provides additional evidence for causation. Some epidemiologists prioritize ruling out chance, bias and confounding to derive causation from association over Hill's criteria. To sum up, association is observed and causation is inferred. Hill's criteria can be used to derive causation from association. Thanks for watching the video.