In a cohort study, you start with exposure in healthy subjects and you check for the outcome of interest. So you have one group who are exposed and another who are not exposed. You follow both of these groups of people, and check who developed the disease or outcome of interest, that is, you calculate the incidence of disease in both groups. And as you have already learnt, relative risks measure the likelihood of getting the disease if you are exposed relative to if you are not exposed. Relative risks can be calculated by dividing the incidence in the exposed, by the incidence in the unexposed Now, I will work through an example of how to calculate and interpret the relative risk in a cohort study examining the association between smoking and lung cancer. Let's imagine a study enrolls 200 smokers and 200 nonsmokers. Both groups are followed up for 20 years for the development of lung cancer. 60 of the smokers develop lung cancer and 20 of the nonsmokers develop lung cancer. OK, let's start by constructing a 2 by 2 table. It is standard practice to put disease or outcome along the top of the table. So here that is lung cancer and no lung cancer. Exposure stages will then go along the side, so in this case smoker and nonsmoker. You know 60 of the 200 smokers enrolled in the study developed lung cancer, and 20 of the nonsmokers developed lung cancer. So if you slot this information into the table, it should look like this. After completing the 2 by 2 table, you can now check for an association between smoking and lung cancer, by calculating the relative risk. The relative risk here is simply the ratio of the probability or risk of developing lung cancer in the smokers group, divided by the risk of developing lung cancer in the nonsmokers group. So the risk of developing lung cancer as a smoker is the number of smokers who develop lung cancer 60, divided by the total number of smokers, 200. So that is equal to 0.3, or 30%. The risk of developing lung cancer in the nonsmokers is the number of nonsmokers who develop lung cancer, 20, divided by the total number of nonsmokers, 200. So that is 0.1 or 10 percent. To calculate the relative risk, you simply divide these 2 figures, 0.3 divided by 0.1. This gives you a relative risk of 3. So in this particular study, people who smoke are 3 times more likely to develop lung cancer compared to nonsmokers. Therefore, smoking appears to be a risk factor for lung cancer. Calculating relative risks is as simple as that. Hopefully, you now understand where the numbers come from when you've read that a cohort study reports a relative risk of say for example, 3.