Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

Null Hypothesis

MSBMSB
edited April 2016 in JASP & BayesFactor

Hi,

I am suddenly not sure about the null hypothesis when computing BFs for t tests and correlations in JASP:
When I specify that my alternative hypothesis (H1) do be one-sided, what is the BF computed against?
is H0 that t/r=0?
or is it complementary of my H1 (such as if H1:r>0, H0:r<=0)?

Thanks,
M

Comments

  • edited 4:22PM

    Hi,

    If my understanding is correct, you only specify H1 here. H0 is always a real null hypothesis, i.e. that there is no difference/ correlation. There is no need to for H0 and H1 to jointly cover all conceivable effects.

    Cheers!
    Sebastiaan

    There's much bigger issues in the world, I know. But I first have to take care of the world I know.
    cogsci.nl/smathot

Sign In or Register to comment.