What does statistical power represent?

What does statistical power represent?

• A. The probability of making a Type I error.
• B. The probability of obtaining a significant result when the null is true.
• C. The probability of detecting an effect when it exists.
• D. The size of the effect.

Answer: (C)

Statistical power is the probability of detecting an effect when one truly exists. In other words, it’s the chance you’ll correctly reject the null hypothesis if the alternative hypothesis is true. Power is 1 minus the probability of a Type II error (failing to detect a real effect). It rises with a larger true effect, larger sample size, and lower variability, and it can increase with a higher alpha level (though that also raises the risk of a false positive). Researchers often aim for power around 0.80 or higher to have a good likelihood of finding real effects. The other ideas described—likelihood of a false positive, or the mere size of the effect—are related concepts but not what power measures.

Statistical power is the probability of detecting an effect when one truly exists. In other words, it’s the chance you’ll correctly reject the null hypothesis if the alternative hypothesis is true. Power is 1 minus the probability of a Type II error (failing to detect a real effect). It rises with a larger true effect, larger sample size, and lower variability, and it can increase with a higher alpha level (though that also raises the risk of a false positive). Researchers often aim for power around 0.80 or higher to have a good likelihood of finding real effects. The other ideas described—likelihood of a false positive, or the mere size of the effect—are related concepts but not what power measures.