Closed DominiqueMakowski closed 6 years ago
I'm not sure what you mean; the Bayes factor is as sensitive as the method should be. For what it's worth, the p value is at the limit of numerical precision as well (<2.2e-16).
Alright it was the question that I asked that was wrong. Thanks for your answer :)
I am trying to compare large normal distributions (n > 1000) to mu = 0. However, the bayes factor becomes quickly very large (or infinite), even though visually the distribution is relatively close to 0 (a large proportion of it overlaps 0 and the opposite side).
Is there any less sensitive alternatives? That would require larger deviations to consider evidence for alternative hypothesis?
Thanks