JASP 0.8.1
Hi everyone!
I have a quick question - on Twitter it said that this JASP update contains the possibility for subjective priors for some tests but that subjective t-test priors would be in the next update. Which tests have the possibility for subjective priors in this update? :-)
I am using Bayesian within-subjects ANOVA and was interested in seeing how the change of prior would affect my results.
All the best
eniseg
Comments
The binomial test allows a subjective prior (through the parameters of the Beta distribution). In the next versions we add a subjective prior for the t-tests, and possibly the correlation. The ANOVA requires more work though. Honestly, I would simply stick to the default priors.
Cheers,
E.J.
Hi E.J.,
Thank you so much! I've read your Part I and Part II Introductions and found them very helpful.
I've considered sticking to default priors, just been worried I might get criticised for not having subjective priors because in my field there is a lot of evidence that over the course of polar missions, mood becomes worse. The priors I had in mind were based on that. Can I justify sticking to default priors despite this?
Also, I'm a big fan of the pizza plot and not just because of its name. From what I can see, the prior/posterior and robustness plots with the pizza plot aren't available for ANOVA, right? Or am I missing the button to click?
Best,
Anna
Hi Anna,
No, pizza plots aren't available for ANOVA. I guess the reason is that there are so many models, and so many Bayes factors. There is such a thing as too much pizza.
With respect to the priors, you raise an important point. If you have a specific ordering in mind, the correct analysis is really based on the definition of contrasts. We are working to implement this, but it's not in JASP just yet. But Richard Morey has done a post on how to do this using his BayesFactor package in R.
Cheers,
E.J.