Justifying "default prior" in JASP

EmilieC

In our study, we used the default prior in JASP to compute BFs since the comparisons we had were not reported in any former studies. We used the default prior for all our analyses (repeated-measures ANOVA, t-tests, correlation, etc.). One reviewer nonetheless asks us to list the default priors used in JASP and to explain them.

I have checked in the manual for Students, but I don't find relevant information on which default prior are used and why.

What would be the most relevant literature to mention for this? I was wondering if the following papr was the most appropriate:

Ly, A., Verhagen, J., & Wagenmakers, E. J. (2016). Harold Jeffreys’s default Bayes factor hypothesis tests: Explanation, extension, and application in psychology. Journal of Mathematical Psychology, 72, 19-32.

Thank you very much for the help!

eduard

Hi Emilie,

One starting point to check the priors is this paper: https://link.springer.com/article/10.3758/s13423-017-1323-7

If this is not enough, EJ will be able to tell yo more.

Eduard

EJ

For ANOVA, the reference is Rouder et al. (2012) JMP. This is not trivial to explain!

For t-tests. one reference is Jeffreys, 1961, as explained in Ly et al., 2016. For the default prior width you can refer to the BayesFactor package and its documentation.

For correlation, the reference is Jeffreys, 1961. If you look on my website you'll see various papers using that correlation test.

As an aside, when you expand the triangle in the JASP output, and go "copy citations", this will put the relevant material in your clipboard.

Cheers,

E.J.

EmilieC

Thank you very much for those references!

Emilie