- Statistical power (1 - β) is the probability of rejecting a false null hypothesis. In other words, it is the chance of finding an effect that truly exists in the population.
- Statistical power is a direct function of both Type I (α) and Type II (β) error.
- In any given study, we always want to maximize our statistical power.
- Statistical power is influenced by four factors: alpha level, sample size, effect size, and whether the test is directional or nondirectional.
- Of the four factors that affect statistical power, the only one not under the direct control of the researcher is effect size.
- The factor that has the largest impact on statistical power is sample size. Sample size increases power by reducing the standard error of the sampling distribution used in the test.
- Always consider the statistical power of a test when you fail to reject the null hypothesis.
- Think about the statistical power of your test while you are planning your study. You always want to have enough research participants to be able to detect the effect of interest.
|
|
|
|
|
|
|
