Biostatistics · Introductory

Risk ratio

Written by SignalsLab

Early edition: these lessons are being reviewed.

Content

Summary

The risk ratio, or relative risk, is a measure used in cohort studies to compare the probability of an event occurring in an exposed group versus an unexposed control group. It is calculated by dividing the risk in the treated group by the risk in the control group, where a value of 1 indicates no difference, values greater than 1 indicate increased risk, and values less than 1 indicate reduced risk. Interpretation must be supported by 95% confidence intervals; if the interval includes 1, the result is not statistically significant.

Intuition

Think of the risk ratio as a comparison tool for two groups over time, specifically in cohort studies where we follow people to see who develops an outcome. Risk itself is simply the probability of an event happening, calculated by dividing the number of events by the total number of people at risk. For example, if one in every 100 patients suffers a side-effect, the risk is 0.01. The risk ratio then compares this probability between an exposed group and a control group. If the ratio is 1, there is no difference in risk. If it is greater than 1, the event is more likely in the exposed group, and if it is less than 1, the event is less likely. However, a single number is not enough; we must look at the 95% confidence interval to determine statistical significance. If that interval includes the value 1, we cannot rule out the possibility that there was no real difference between the groups. It is crucial to distinguish this from odds, which are used in case-control studies, and to remember that relative risk reduction can be misleading without considering absolute risk reduction.

Key equations

Risk=number of eventsnumber of people at risk
(1)

Risk is the probability of an event occurring, calculated by dividing the count of events by the total population at risk.

RiskRatio=Risk in treated/exposed groupRisk in control/unexposed group
(2)

The ratio comparing the probability of an event in the exposed group to that in the control group.

Odds=number of times event happensnumber of times event does not happen
(3)

Odds represent the ratio of the occurrence of an event to its non-occurrence.

Derivation

  1. Define risk as the probability of an event occurring, calculated by dividing the number of events by the total number of people at risk.
  2. Identify the study design as a cohort study, which is prospective and follows a group over time to investigate the effect of a treatment or risk factor.
  3. Calculate the risk in the treated or exposed group.
  4. Calculate the risk in the control or unexposed group.
  5. Divide the risk in the treated/exposed group by the risk in the control/unexposed group to obtain the risk ratio.
  6. Interpret the risk ratio: a value of 1 indicates no difference, values greater than 1 indicate increased risk, and values less than 1 indicate reduced risk.
  7. Calculate the 95% confidence interval for the risk ratio.
  8. Determine statistical significance by checking if the confidence interval includes the value 1; if it does, the result is not statistically significant.

Worked example

Problem

In a study of football players, the risk of breaking a leg is 0.012 for players and 0.004 for non-players. Calculate the risk ratio and interpret the result. Additionally, if the 95% confidence interval for this risk ratio is 0.97 to 9.41, is the result statistically significant?

  1. Identify the risk in the exposed group (football players) as 0.012.
  2. Identify the risk in the control group (non-players) as 0.004.
  3. Calculate the risk ratio by dividing the risk in the exposed group by the risk in the control group: 0.012 / 0.004 = 3.
  4. Interpret the risk ratio of 3: since it is greater than 1, the rate of breaking a leg is increased compared to controls.
  5. Examine the 95% confidence interval, which is 0.97 to 9.41.
  6. Check if the confidence interval includes the value 1. Since 0.97 < 1 < 9.41, the interval includes 1.
  7. Conclude that because the confidence interval includes 1, the result is not statistically significant, and one cannot exclude the possibility that there was no difference in risk between the groups.

Answer The risk ratio is 3, indicating increased risk. However, the result is not statistically significant because the 95% confidence interval (0.97 to 9.41) includes 1.

Common mistakes

  • Interpreting odds ratios as risk ratios for common events, which yields different values.
  • Confusing risk (probability) with odds (ratio of event to non-event).
  • Overestimating drug efficacy by focusing only on relative risk reduction while ignoring absolute risk reduction and number needed to treat.
  • Assuming a risk ratio result is significant if the confidence interval includes 1.
  • Using risk ratios in case-control studies instead of odds ratios.

Animation

Animation coming soon

The animated version of this lesson is being prepared for the web. In the Signals AI app, lessons are drawn step by step.

Code

This is a text lesson: it has no animation code yet.

ccBYNC© 2026 SignalsLab. Lesson text shared as is under CC BY-NC 4.0.