Statistical power is the chance that a study will detect a real effect when one actually exists. Power rises with bigger samples, bigger effects and less variability in the data.
Why it matters
A study with low power can miss a real effect and wrongly conclude there is none. That is why researchers value large samples and why a meta-analysis, which pools many studies, gives a more reliable answer than one small study.
How the exam tests it
A typical item describes a meta-analysis of 85 studies on therapy for depression and asks for its main advantage. The answer is that pooling the studies greatly raises power and gives a more stable estimate of the overall effect.
Don’t confuse it with
Students confuse power with statistical significance, but significance asks whether one result is unlikely to be chance, while power asks how likely a study was to find a real effect in the first place.