Relative risk and efficacy using AstraZeneca vaccine trial

The aim of new treatment interventions such as vaccines, is to lower the risk of disease. This is a very topical discussion as many vaccines have been, or are currently, subjected to clinical trials.

These trial express their results as efficacy. Efficacy is calculated from relative risk. It is hoped that a vaccine will lower the risk of infection when compared to placebo.

In this video tutorial, I use the R language for statistical computing to explain risk, relative risk, efficacy, and most importantly, confidence intervals for efficacy.

In February 2021 South Africa received their first batch of vaccines (Astra Zeneca). Prior to a roll out to healthcare workers a small trial appeared which showed efficacy of only 21%. For this, and other findings in the trial, the vaccine was withdrawn.

Because the trial was so small and the risk of developing mild and moderate COVID-19 was low in each group, the confidence intervals around the efficacy was very wide.