When can correlation equal causation?
A major goal of epidemiology and biostatistics is the establishment of causal relationships. A ‘cause’ of disease is an event, condition or characteristic that plays a role in producing the disease or if the operation of it increases the frequency of the event. Not all associations and correlations are causal.
Need to decide if the relationship is:
• Risk factor
• Part of natural history
• Chance/random association
Sufficient cause – something that inevitably produces the disease – the causal factor always results in the outcome.
Necessary cause – the outcome occurs only if the causal factor has operated.
Factors in causation:
• Predisposing factors – those that create a state of susceptibility so that the host can react to a disease agent (eg age; previous illness)
• Enabling factors – assist in the development of the disease (eg income; availability of health care services)
• Precipitating factors – associated with the onset of a disease or state (eg exposure to a specific agent)
• Reinforcing factors – those which aggravate a disease or state once this is already present
Guidelines for Establishing the Cause of a Disease:
• Temporal relationship – does the cause precede the effect?
• Plausibility – is the association consistent with other knowledge?
• Consistency - have similar results been shown in other studies?
• Strength – what is the strength (relative risk) of the association between the cause and effect?
• Dose-response relationship – are varying amounts of exposure to the possible cause associated with varying amounts of the effect?
• Reversibility – does the removal of a possible cause lead to the reduction of disease risk?
• Study design – is the evidence based on a string study design?
• Judging the evidence – how many lines of evidence lead to the conclusion?
Strength of cause:
Vaccines and Blue Foot Syndrome