# Help with hypothesis forming

#### philip.coggle

##### New Member
Hi All,

I am newbie to statistics.

When I read the literature regarding null hypothesis, I understand that the null hypothesis should always include equals to sign (= , <=, >=). In my research, i am trying to prove that a variable is equal to zero in all my experiments.

I am confused about how to write the null hypothesis.

Is it ok to write a null hypothesis that the mean is not equal to zero and the alternate hypothesis that the mean is equal to zero.?

Can you please help?

Many thanks in advance!

Regards
Phil

Last edited:

#### hlsmith

##### Less is more. Stay pure. Stay poor.
You got it. Though if you want, you don't have to have = signs, you design your own hypotheses. It just so happens most use = to make test two sided and error on the side of caution.

#### Karabiner

##### TS Contributor
Is it ok to write a null hypothesis that the mean is not equal to zero
The statistical null hypothesis is the hypothesis to be nullified,
but you cannot reject the hypothesis that the mean is
not equal to zero. This would mean that you prove
that the mean is eqal to zero, which is not possible.

Since your research question seemingly requires some
kind of -> (one sample-) equivalence test(ing), I'd suggest
that you do some research on how statisticalhypotheses are
set up within that approach.

With kind regards

K.

#### philip.coggle

##### New Member
Karabiner, Miner and Hlsmith, Many thanks for taking time to help me and point me in the right direction. I have been breaking my head over this issue over the last few days. You saved me.