EJ
About
- Username
- EJ
- Joined
- Visits
- 2,530
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
JASP includes the Shapiro-Wilk test under "Descriptives" -> "Statistics" -> "Distributions". However, what is at issue here is whether the residuals are normally distributed. For this we offer QQ plots and plots o…
-
Hi Camille, Sorry for the tardy response. I do think LMM is a good way to address these questions. I am not an expert on these models, however, and the team that has implemented them in JASP is still in the process of writing a tutorial. I do believ…
-
Hi Alexa, Sorry for the tardy response. My gut says to either half or double the default. But I'll contact the team for a more informed opinion... Cheers, E.J.
-
Hi Samra, We are working to make the R syntax available for the analysis in the modules, and hope to have that done soon. As far as expert help is concerned, I would first point you to tutorial papers (these should be in the help file). Cheers, E.J.
-
Hi Nathalie, Technically, the simulated data ought to be generated from the fitted model. Also note that you can simulate from H0, from H1 (using the information already obtained) or both (using model averaging). Cheers, E.J.
-
If the columns are fixed, then each column is a group. Group one will be the first column, group two will be the second column. So yes, the proportions are compared across the columns. The sample proportions for each column are obtained from the inf…
-
Dear Radamanthus, First, I would strongly suggest the Bayesian A/B test for this design; see https://psyarxiv.com/z64th and https://onlinelibrary.wiley.com/doi/10.1002/sim.9278 for instance. Second, this is an independent multinomial. The joint mult…
-
(if we don't have it, it would be a good feature request for our GitHub page) E.J.
-
We offer several correction for multiplicity, but somehow I can't seem to find this one quickly. I'll ask our expert. Cheers, E.J.
-
Sorry about the tardy reply. I know that this is possible in our ANOVA and regression. I've just asked our expert about LMMS! Cheers, E.J.
-
Hi DT, Ah, this is an interesting question (and sorry about the tardy response). I would say that the credible intervals that are reported are conditional on H1, and therefore do not need a correction. However, the unconditional credible intervals i…
-
Hi Whirly123, This is an interesting question. Note that a BF (for H0 vs H1) is related to a p-value approximately as 3*p*sqrt(n), see https://psyarxiv.com/egydq So in a way a Bayesian does optional stop on a p-value, but with a sample size correcti…
-
Hi Julia, Good question -- I'll forward this to our expert. Sorry about the delay. Cheers, E.J.
-
Dear Dayna, Sorry about the delay. I'll forward your question to our expert. It does seem as if the image you tried to attach is broken though... Cheers, E.J.
-
Hi Georgios, Issue 1 looks more like a bug (unless it is explained in the help file). If it is not explained in the help file, please post it on our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/). Is…
-
Hi Mels, Sorry for the tardy reply. For the test of two proportions, I would use the Bayesian A/B test -- I think it is more in line with the hypothesis you want to examine. See https://psyarxiv.com/z64th and https://onlinelibrary.wiley.com/doi/10.1…
-
Dear Grzegorz, Thanks! The guidelines for translation are at https://jasp-stats.org/translation-guidelines/ We use weblate, and I think it should be possible to find the information of the translators there. Of course you are also welcome to join in…
-
Hi Mariana, The output table will present the best 10 models, so the models with the highest posterior probability. This may include the null model. It is true that the repeated measures models take a long time to run, especially for complex designs…
-
no worries, thanks for letting us know! Cheers, E.J.
-
Thanks, I attended the experts to this question.
-
You can find Generalized Linear Model under "Regression" E.J.
-
Not yet. A first step is outlined here (https://jasp-stats.org/2023/03/06/r-syntax-mode-in-jasp-the-first-button/), and in a few months we hope to have R code that runs inside R Studio (currently it runs only in the JASP R Console). As an aside, I d…
-
Update: there was indeed a glitch with the servers, but luckily that was resolved quickly. EJ
-
Strange. I just tried this and it works for me. Maybe a temporarily glitch? Could you try again and see whether it works? The best home for this issue is our GitHub page, by the way (for details see https://jasp-stats.org/2018/03/29/request-feature-…
-
Dear XuhuiZhang, The beta-binomial formulation is based on an idea by Harold Jeffreys that was elaborated upon by Scott & Berger (2006,2010) -- references are hopefully in the help file. The idea is that a beta(1,1) prior assigns equal prior pro…
-
One of our core programmers is working on this full time. We'll do an interim release in May and then this functionality is next -- before the summer (99% sure). E.J.
-
This strikes me as problematic EJ
-
That depends on your resources and the importance of the test. Also, you could do a Bayesian power analysis at this stage and assess the probability of finding could evidence if you continue for the next N trials (e.g., https://psyarxiv.com/9sazk/).…
-
I think we could probably add a note underneath the table. On the other hand, I am not married to this particular setting, and if most programs have a different default then I don't see why we ought to stick religiously to the current setting. E.J.
-
I forwarded this to the team EJ