Deck 9 – Hypothesis Testing (LM8)

In hypothesis testing, why does a small $p$-value lead you to reject $H_0$?

The sample result would be unlikely if $H_0$ were true.

What does statistical power measure?

$P(\text{reject }{H}_0\mid H_0\text{ is false})=1-\beta$.

What changes increase the power of a hypothesis test?

Higher $n$, larger effect size, lower $\sigma$, or higher $\alpha$.

Why is it wrong to interpret the p-value as the probability that $H_0$ is true?

It is the probability of data this extreme assuming $H_0$ is true.