
A Cluster Trial Assigns Groups, So Count the Groups as Well as the People
A trial involving hundreds of people may have randomised only a small number of clinics, schools or communities. The number of participants and the number…

A trial involving hundreds of people may have randomised only a small number of clinics, schools or communities. The number of participants and the number…

An interview study may offer a detailed account of why people find a service difficult to use. Its value does not depend on converting every theme into a…

In a crossover trial, a participant may receive one intervention during one period and another during a later period. The comparison is organised…

People in a trial may stop an assigned intervention, change what they receive or use it differently from the plan. How researchers analyse those…

A headline may call a result statistically significant without saying how much changed. That leaves out information a reader needs to understand whether the…

A study can report a change in a laboratory marker without directly measuring whether participants live longer or feel better. The measured indicator may be…

Knowledge of a treatment assignment can influence expectations, reporting, or assessment. Blinding aims to limit that influence, but the label is more…

The word “random” can describe how people enter a study or how enrolled participants are assigned to groups. Those are different steps, and one does not…

A study may follow people with different habits and compare later outcomes. That design differs from a trial in which researchers assign an intervention,…