Absolute Risk

The probability that an individual in a defined population will experience a specific outcome over a given period, without reference to a comparison.

Source: Rothman KJ, Greenland S, Lash TL. Modern Epidemiology. 3rd ed. Lippincott Williams & Wilkins; 2008.

Absolute risk is the probability that a person in a defined group will experience a particular outcome over a stated period, expressed on its own without comparison to another group. It says directly how likely the event is for that individual, such as a one-in-twenty chance over ten years, which is what a patient most naturally wants to know. Because it stands alone, it conveys the true magnitude of a risk in a way a ratio between groups cannot. A plain probability of the event is what it gives. Rothman and colleagues (2008) describe this.

Source: Rothman et al. 2008

Absolute risk is the actual probability of an outcome in a group, stated on its own, while relative risk compares the risk between two groups as a ratio. Absolute risk tells how likely the outcome is; relative risk tells how many times more or less likely it is in one group than another. A relative risk conveys the strength of an association but not the underlying probability, so the same relative risk can correspond to very different absolute risks depending on the baseline. So absolute risk gives the actual likelihood and relative risk the proportional comparison, and both are needed to interpret risk fully.

Source: Rothman, Greenland & Lash 2008

Absolute risk is important because it conveys the actual likelihood of an outcome, which is what patients and clinicians need to judge how concerning a risk is and to make decisions, and which relative measures alone do not provide. A large relative increase in risk may still leave the absolute risk small if the baseline is low. So absolute risk matters for the meaningful communication and interpretation of risk, since understanding how likely an outcome actually is, not only how it compares between groups, is central to informed decisions about treatment and prevention, and to avoiding the exaggeration that relative measures can create.

Source: Rothman, Greenland & Lash 2008

Absolute risk is calculated as the number of individuals experiencing the outcome divided by the total number in the defined group over the specified period, giving the proportion or probability of the outcome. It requires a defined population, outcome, and time period. So absolute risk is calculated directly from the frequency of the outcome in a group, expressing it as a probability, which forms the basis for comparing groups through differences or ratios, since absolute risks in different groups are combined to give measures such as the risk difference and the risk ratio, and its calculation depends on clearly specifying the population and period.

Source: Rothman, Greenland & Lash 2008

Absolute risk relates to absolute risk reduction in that the absolute risk reduction is the difference between the absolute risks of an outcome in two groups, typically a control group and a treatment group. The absolute risks are the actual probabilities in each group, and their difference measures how much the treatment changes the risk in absolute terms. So absolute risk is the building block from which absolute risk reduction is derived, since subtracting the absolute risk in the treated group from that in the control group gives the reduction, which conveys the practical benefit of the treatment on the scale of the outcome.

Source: Rothman, Greenland & Lash 2008