Interpretation of one and two-sided Bayesian t-tests for independent groups

Izymil

Hi group!

I have performed Bayesian Mann-Whitney test in JASP.

When I test H1: 1>2, Bayes factor is inconclusive

When I test H1: 1~=2, BF is moderately on a side of H0

When I test H1: 1<2 BF i strongly on a side of H0.

I think that the proper interpretation would be that either the groups are equal or the 1>2.

There is no conclusion which of these two possibilities should we believe more , but we can quite firmly discard the possibility 1<2. Am I right? Can I draw such a joint conclusions from three tests?

1 smaller that 2.png

1 not equals 2.png

1 larger than 2.png

EJ

Correct. The sample effect is slightly positive, so changing to a one-sided positive hypothesis is helpful for H1, but changing to a one-sided negative hypothesis is harmful for H1 (because the sample effect is in the opposite direction of what H- predicts).

E.J.