A power of 0.8 is typically considered what?

• A. An 80% chance to detect an effect if it exists.
• B. An 80% chance to reject the null when there is no effect.
• C. The effect size is 0.8.
• D. The probability of Type I error is 0.2.

Answer: (A)

Power is the probability that a statistical test will detect an effect if there is one. A power of 0.8 means there is an 80% chance of rejecting the null hypothesis when a real effect exists, given the chosen significance level, true effect size, and sample size. This reflects how likely the study is to find a significant result if the effect truly is present. It doesn’t describe what happens when there is no effect—that would be governed by alpha, the Type I error rate. It also isn’t the size of the effect itself—that’s an effect size like Cohen’s d or a correlation. And it isn’t the probability of a false positive; that relates to Type I error. So the 0.8 power corresponds to an 80% chance of detecting an effect if one exists.