Which statement best describes statistical power in hypothesis testing?

• A. The probability of observing a result as extreme by chance.
• B. Probability of detecting a true effect.
• C. The probability that the null hypothesis is true.
• D. The probability of a Type I error.

Answer: (B)

Statistical power is the probability that a hypothesis test will correctly reject the null hypothesis when a real effect exists. In other words, it’s the chance of detecting a true difference or association if it really is there, and it equals 1 minus beta (the probability of a Type II error). Power increases with larger true effect sizes, larger sample sizes, less variability in the data, and, to some extent, a higher alpha level (though that also raises the chance of false positives). A common target is 0.80, meaning an 80% chance of detecting the effect if it truly exists. This concept is not about the probability that the null is true, nor about observing results by chance under the null, nor about the Type I error rate (alpha).