Model averaged R2 lower credible interval is zero
Hi! I ran a bayesian ANOVA (2 groups) and my model averaged R2 lower credible interval is 0 and the upper .3 (even though my BF10 group factor against the Null model is greater I0). Just to be sure, I am right when I say that there is a 95% probability that my found effect is in a next study probably a Null effect? If this is the case it would be the deadblow for any publication, right?
Is there any good advice how I should present/interpret these results or would you move towards saying probably better not to publish such results?
Thank you!
Best
Markus
Comments
Hi Markus,
Can you paste the model table? If the BF supports the inclusion of the group factor than this is what counts. The model-averaged R2 credible interval informs you about the size of the effect, not about whether it is present or absent -- if publication depends on how compelling the stats are (which is unfortunate, but still the world we live in), then what counts most is the BF.
Cheers, E.J.
Hi E.J.,
Thank you very much for your time and the response!
I put two tables and the model averaged Q-Q plot in the attachment.
Best,
Markus
Yes, so the model including Groups get strong support from the data (over the null model).
You might want to look at R2 that is not model-averaged, but based on the model including Groups.
Cheers,
E.J.
Great E.J., thank you very much! I will do that!
All the best,
Markus