Two-sample t-test variant?

I have a situation that is the opposite of the usual two-sample t-test for equal means: I'm trying to show that it's statistically unlikely that two samples are different.

Is there a statistical test that has the null hypothesis being that the two samples are unequal, and the alternate hypothesis being that the two samples are equal? The number of samples in these tests is small (5 samples each), so I need an equivalent to the t-test, not to the z-test.

Thank you for your help!

flag	asked Jun 24 2011 at 4:05 chipuni 13●2

Try stats.stackexchange.com - it is more statistics oriented than MO. – David Roberts Jun 24 2011 at 4:16

Thanks, David. I didn't know about that site. – chipuni Jun 24 2011 at 4:27

This question is quite unclear. Why would one not simply let the null hypothesis be equality of population means? That's what you'd normally do if you're hoping the data will justify the conclusion that they're not equal. – Michael Hardy Jun 25 2011 at 20:42

Browse other questions tagged st.statistics inequalities or ask your own question.

question feed