# Bayesian Assumptions

Hi Everyone,

I've just found the paper called "The JASP Guidelines for Conducting & Reporting a Bayesian Analysis" and I'm really enjoying the read. It's so clearly written, and so easy to follow. It mentions assumptions for Bayesian analyses thought which I wasn't familiar with despite having read "Bayesian Inference for Psychology" Parts I and II, and other Bayesian papers.

Is there a good paper that goes over the assumptions? Are Bayesian assumptions very different from frequentist ones?

Also, I noticed that the dependent variable used in the Stereogram example is log-transformed. Was this done because of the non-normality of the data? It's not mentioned in the pre-print (I think it's a pre-print). Is transformation mandatory, even when you're using the Mann-Whitney test

Best wishes

eniseg2

## Comments

Hi eniseg2,

Thanks for the positive comments about the paper!

Bayesian assumptions are generally the same as the frequentist ones.

Yes, the DV for the stereogram example is log-transformed in order to remove the right-skew. Reviewers asked us to elaborate on that point, so we will do that. And yes, it is a pre-print (but under revision for Psychonomic Bulletin & Review). For rank-based tests such as MW, it doe snot matter whether or not the data are transformed (as long as the transformation is monotonic, such that the rank information is unaltered, as is the case for the log transform).

Cheers,

E.J.