2
$\begingroup$

Problem: I have two sample groups(A and B), each with more than 30 samples. I want to know if the mean of A is 5% more than mean of B. Is z test a proper way to go here?

Online I found most of z test is testing hypothesis that if mean of A and B are different or not at confidence level of say 95%, but not testing if they are different for more than x%. Could anyone suggest a way here? Thanks a lot!

$\endgroup$

1 Answer 1

-1
$\begingroup$

You can just use the normal formula, but subtracting .05 from the numerator. That is, where $p_A$ and $p_B$ are the two proportions, the numerator can be written as $p_A - p_B$, and you can replace this with $p_A - p_B - 0.05$.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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