Randomized controlled trial

A randomized controlled trial (RCT) is an experimental study in which participants are allocated by chance, often by a computer-generated sequence, either to the intervention being tested or to a control group that receives a placebo, the usual treatment or nothing. The groups are then followed and their outcomes compared. Unlike in observational studies, the investigator decides who receives the exposure.

Randomization is what gives the design its strength. Because chance alone decides allocation, the groups end up similar in age, health and countless other characteristics, including ones nobody thought to measure, so a difference in outcome can reasonably be attributed to the intervention itself. Further safeguards include allocation concealment, in which recruiters cannot know the next assignment, and blinding, in which participants and researchers do not know who received what. Results are usually analyzed by intention to treat, keeping everyone in the group they were assigned to.

RCTs are regarded as the gold standard for testing new drugs, vaccines and other treatments. They are expensive and slow, though, volunteers may not resemble the wider population, and some questions, such as whether a harmful habit causes disease, cannot ethically be tested this way.