3
$\begingroup$

I'm wondering how do we decide the "shape" of region of rejection in a hypothesis testing problem. Let's take a two-tailed z-test as an example. What if we choose the weird-looking region of rejection on the left instead of the more widely-used one on the right?

While I intuitively believe choosing the classic one is a better idea, the significance level of both tests are 0.05, so what makes one superior to the other?

$\endgroup$

1 Answer 1

2
$\begingroup$

what makes one superior to the other?

The power of the left one is much lower than that of the right. To quote the Wikipedia entry:

The power of a binary hypothesis test is the probability that the test correctly rejects the null hypothesis (H0) when a specific alternative hypothesis (H1) is true.

Talking about significance without power doesn't have much meaning. You could simply ignore the observations, generate a random number between 0 and 1, and reject if less than something predetermined, for example.

$\endgroup$
1
  • $\begingroup$ This answer looks convincing but I just cannot wrap my mind around this: is power related to the power function? Also since the power function is continuous, we can say $\alpha + \beta = 1$ at the “juncture” of H0 and H1. Thus, increasing power means reducing $\beta$, which would also increase $\alpha$, and that doesn’t seem good to me.., $\endgroup$
    – nalzok
    Jun 3, 2018 at 3:00

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.