Moderate# Two-Proportion Test: Power

APSTAT-TEEFAD

Which of the following statements is/are NOT true about power in the context of a two-proportion test?

I.Large sample sizes will often allow the statistician to find a significant difference between the two proportions if one really exists.II.Low alpha levels will allow the statistician to find a significant difference between the two proportions if one really exists.III.Power will be $1$, the probability of a type I error.