# Probably a silly question

#### mikhail_ohara

##### New Member
I'm not sure if I'm posting in the right section and my question is probably very basic. But here it goes...

If I'm running a two-tailed independent-samples t-test and P=.01, I can reject the null hypothesis, but can I look at the means and state that one is significantly higher than the other when neither the null nor alternative hypotheses state that. Say I'm comparing number of eggs, and one mean is 160 and the other is 80. Can I only conclude that they're different with a two-tailed test? Or can I also state that one is significantly higher than the other even through the alternative hypothesis doesn't state this? Any help would be appreciated. Thank you.

Mike

#### GretaGarbo

##### Human
I can reject the null hypothesis, but can I look at the means and state that one is significantly higher than the other when neither the null nor alternative hypotheses state that.
Yes.

can I also state that one is significantly higher than the other
Yes you can.
I have seen the formalism in multiple inference for that yes you can conclude that. (Although I can't remember the formalism now.)

And besides, anybody would spontanously conclude that.
(And it is certainly not a silly question.)