Measure of Assocation - Risk Ratio

Lead Author(s): Jeff Martin, MD

Definition of Risk

In a cohort study:

Risk is based on proportion of persons with disease = cumulative incidence

The concept of risk reflects the proportion of persons experiencing the event or outcome or disease.

Definition of Risk Ratio

Risk ratio = ratio of 2 cumulative incidence estimates = relative risk

If the concept of risk reflects the proportion of persons experiencing the event or outcome or disease,

Why Use Risk Ratio?

Risk ratio gives a relative measure Because a ratio measure gives the incidence in one group relative to another, the magnitude of the ratio reflects the strength of the association between the exposure and the disease.

Example of Absolute versus Relative Measure of Risk

In practice many risk factors have a relative measure in the range of 2 to 5.

In the table below it looks like a ratio of about 3, treating more than 3 months really does make a difference,
0312_2tb.JPG

If incidence is very low, relative measure can be large but difference measure small.

Example of Risk Ratio in a Cohort with Complete Follow-up

This is an example (below) from an outbreak of gastrointestinal illness of a risk ratio from cohort data.
0313_1riskratio.JPG

Because the follow-up is short and identical for everyone, the risk ratio is just the ratio of the proportion Eleven is a large value for a risk ratio but that might be expected in a study such as this looking for a single likely food source for the outbreak.

So the RR=11 is taken as strong evidence for assigning causality to eating the potato salad. It is highly likely that the potato salad caused the outbreak of gastroenteritis.

Risk Ratio in a Cohort with Censoring

In many cohort studies there is unequal follow-up time and consequently censoring.

Follow-up in these cohorts, which are not very short term outbreak investigations, have differing amounts of follow-up time on the subjects.

The risk of the event has to be estimated:
  1. in the exposed and
  2. in the unexposed group

Example of Risk Ratio in a Cohort with Censoring

In the Kaplan-Meier analysis of the survival in two groups (below), you have to choose a point in time.

For Example: At 6 years, % dead in low CD4 group = 0.70 and in high CD4 group = 0.26.

Risk ratio at 6 years = 0.70/0.26 = 2.69

0313_3testkm.JPG

As you can see from inspecting the curve, the risk ratio will be different for different points in time.

NOTE : Risk ratio would be different for different follow-up times.