Methodology – Power
Statistics:
Power calculations are used to decide how many patients are needed in a trial. They depend on the clinically significant effect which researchers have to define and the mean and standard deviation of the primary outcome.
A type 1 error happens when the researcher wrongly concludes that an intervention works.
A type 2 error happens when the researchers wrongly conclude that an intervention has no effect.
Power is 1 – the chance of a type 2 error.
Put simply, it means the chance of detecting a difference between the groups if one truly existed.