EJ
About
 Username
 EJ
 Joined
 Visits
 147
 Last Active
 Roles
 Member, Administrator, Moderator
 Thanked
 10
Comments

Hi PeteRose1, There is an earlier discussion on this, see https://forum.cogsci.nl/index.php?p=/discussion/4092/reviewerwantsjustificationforthedefaultprior#latest Cheers, E.J.

Hi Arran, The flat Pearson prior translates to a curved Kendall prior. So if you repeatedly generate large fake data sets by values of rho drawn from a flat Pearson prior, and you estimate Kendall's tau for those fake data sets, the point estimat…

Hi Gareth, This is consistent with subjective Bayesianism. I know Dennis Lindley was of this opinion, for instance, but perhaps it is also mentioned in Edwards, Lindman, & Savage (1963). The idea is that as long as you have specified probabil…

We are working on it! E.J.

Dear Eniseg2, Nothing is wrong (although...see below). If you test whether two groups are different, and all you see are data from one of the groups, the BF should remain exactly 1. I am not so sure about the role of the 10th participant, however…

Hi arran_reader, This is because of the connection between Pearson's rho and Kendall's tau. See the section on "parametric yoking" here: http://www.ejwagenmakers.com/inpress/VanDoornEtAlBayesianKendallsTauinpress.pdf Cheers, E.J.

Hi Yoni, A quick note from my holiday destination: Miller and Chapman (2011) is a recent reference on why the interaction complicates the interpretation. The latest edition of the textbook by Andy Field also discusses this. Cheers, E.J.

There isn't (except running the analysis N times, which is tedious). But it would be a good feature request for our GitHub page! Cheers, E.J.

Dear peterosel, Yes, we don't deal with models that include only the interaction term. One of the reasons is that it is a priori rather unlikely to have a perfect crossover interaction. I believe that there is another argument based on transforma…

I'd advise you to use the classical estimates for that. We have one paper in review on this issue, and it will take some time before it is included in JASP. In general, you've hit on one of the missing features; we've already fixed this for linear r…

You also helpfully posted this on our GitHub page, right? Have we responded yet? You could add a screenshot from before and after, to make it perfectly clear.... Cheers, E.J.

Dear S_T, Yes, the Bayesian results indicate evidence against the interaction. This is also evident from the posterior model probabilities [P(Mdata)]. And I agree that this is unexpected, given the results from the classical analysis. These disc…

Dear Yoni, These are some deep questions :) First off, my current thinking is that it is statistically allowed to add covariates that correlate with the grouping variable (it is as if you are adding a factor to a regression model), as long you r…

Hi Meerkat, This is a "BayesFactor"specific question, so I can't answer it confidently. It appears to me that you have several different (crossed) factors, so a linear mixed model would seem most appropriate, and then the best thing is to take i…

Hi Kay, It would be good to see the exact analysis, for instance a screenshot of the critical outcome  right now things remain somewhat abstract. I can always recommend a Bayesian analysis, of course :) Cheers, E.J.

Hi PDN, This is an interesting issue. I assume you are interested in a Bayesian analysis. One way would be to use contingency tables (or loglinear analyses) for the full 2x3 situation, and include order constraints. These order constraints you c…

Hi Marios Unfortunately this is not yet possible. We are aware of the limitation and we are working on a comprehensive solution that allows all plots to be edited. But it may take a while before we get there. Cheers, E.J.

Hi Luchins, I was a little confused by Eduard's message above. In general, if you want to compute a correlation between victory and the number of aces you have to take into account that victory is a binary variable. It seems you would need the po…

It is because the coefficients for categorical variables require a different prior structure, and this is still being sorted out in the BAS package. What you could do is use the Bayesian "ANOVA" (really a linear mixed effect model) and define an ANC…

I'm not allowed to paste the svg file. Will try to find your Email address

Not a strict timeline but it is the logical next step

If you send me an Email I can forward you the internship report by a student, Tim de Jong, who worked on this. E.J.

On the BayesianSpectacles.org blog you will find about 15 posts on "Redefine Statistical Significance". They explain how this can happen. Another explanation is given here: https://link.springer.com/article/10.3758/s1342301713433 Cheers, E.J.

You can also implement this in WinBUGS and use SavageDickey (the Wetzels et al. 2011 PBR approach), or use Stan and the bridgesampling package. E.J.

Hi Sarah, Interesting example! Here's my take on what's going on here. Basically, there is no contradiction. Yes, the credible interval just overlaps with zero, but that does not mean that should be strong evidence for excluding that predictor. T…

I've forwarded your question to Don (who implemented this analysis).

Hi MattO, You might want to check out this paper: http://www.ejwagenmakers.com/2016/LyEtAl2016JMP.pdf Effect size delta is defined as mu/sigma. As an aside, I was a MATLAB user myself, a bunch of my friends use MATLAB, but I have to say that …

Yes, of course. We really ought to make this available on our webpage. I'll attend the relevant team members to this issue (one is on holiday, but I hope we can deal with this request quickly) Cheers, E.J.

Hi Kris, Thanks for your feedback. Our programming team can help you, but in order to do this effectively, we hope that you can post the issue on our GitHub page (see explanation here: https://jaspstats.org/2018/03/29/requestfeaturereportbug…