EJ
About
- Username
- EJ
- Joined
- Visits
- 2,531
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Hi Shiro, Yes, the null model receives most support. There is some evidence against adding the predictors Urea and Calcium, but the degree of that support is not compelling, especially for Urea. If you want to add the interaction as a predictor, you…
-
Hi JDeBeer, You've also corresponded about this issue on our GitHub page, right? In general, I'd say that it is always a good idea to plot the data -- perhaps even the raw data, and/or means with CIs. Cheers, E.J.
-
Well if you throw away condition C then everything is fine E.J.
-
I'll send someone from the team your way... E.J.
-
Yes, this is available in JASP. It uses an R package by Overstall, called "conting". Cheers, E.J.
-
Yeah so the height of the vertical bar refers to the model in which the coefficient is zero; the density of the solid line is under H1, the model in which the coefficient is not zero. Because it is a density, the height at any one point does not ref…
-
Hi Alexa, There are several perspectives here. First, comparing the model with predictor 3 against the model with predictor 2+3, it is evident that adding predictor 2 makes the model worse. The inclusion BFs support the predictors only weakly. This …
-
We are working on Bayesian assumption tests (for now, I guess the frequentist ones will have to do). For Levene's test, we do have a paper, but it's not implemented in JASP yet: https://www.bayesianspectacles.org/preprint-default-bayes-factors-for-t…
-
Dear August Yes I think that makes sense. I am not aware of any other arguments that have been put forward. You can of course also approach this pragmatically and view it as a form of robustness test: if the two analyses given very different answers…
-
Hi Shiro, To answer your question it would help to see a screenshot of the output. Also, there is this preprint that may help you: https://psyarxiv.com/pqju6/ Cheers, E.J.
-
Let me look into that...
-
van den Bergh, D., Clyde, M. A., Raj, A., de Jong, T., Gronau, Q. F., Marsman, M., Ly, A., and Wagenmakers, E.-J. (2020). A tutorial on Bayesian multi-model linear regression with BAS and JASP. Manuscript submitted for publication. https://psyarxiv…
-
Thanks for the link!
-
Dear Nadav, Right now the graphs cannot be edited. Allowing that is one of our top priorities. Cheers, E.J.
-
Thanks!
-
Hi Eliza, I would refer you to these papers: Gronau, Q. F., Ly, A., & Wagenmakers, E.-J. (2020). Informed Bayesian t-tests. The American Statistician, 74, 137-143. https://www.tandfonline.com/doi/full/10.1080/00031305.2018.1562983 Ly, A., Etz, A…
-
Thanks! I'll add this to our GitHub page. For future reference, here's how to do that yourself: https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/ E.J.
-
A few quick remarks: 1. "Specifically, the observed data were approximately 2.2 times more likely under the model where thresholds were predicted by the interaction between group and condition, compared to the model where these were predicted b…
-
Yes. Under the "model" tab, select the variables for which you'd like to see an interaction in "Components", and drag them at the same time to the "Model Terms" box. Dragging them at the same time will add the interacti…
-
Hi Pajafumo, Thanks for your post. This is really an issue for our software development team. You can reach all of them through our GitHub page, for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/. Posting the issue on…
-
Dear Yorgos, The Bayesian hypothesis test for the equality of two correlations is still under development. Cheers, E.J.
-
Hello, >>"The Bayesian one-way ANOVA with two levels does give the same BF as a Bayesian between-subjects t-test (with the default priors)" >Hmmm, it doesn't for me - I just tried it again in JASP. I am using the repeated measures…
-
With few models in play, I would just interpret the standard output table of models. As the model space grows large, it is increasingly attractive to report the inclusion BFs. But nothing is stopping you from reporting both, of course. Just put an a…
-
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 documen…
-
Strange. This is the second time I heard this -- for me it usually downloads immediately. I'll ask some team members for insights... Cheers, E.J.
-
yes (not a principled limitation, but a current limitation in most Bayesian linear regression methods) yes I recommend reporting all that seems relevant. Maybe report the key indicators in the paper, and put an annotated JASP file on the OSF? Cheers…
-
Hi PM, Mann-Whitney is a rank-based test, so I believe its assumptions are very mild. See https://statistics.laerd.com/statistical-guides/mann-whitney-u-test-assumptions.php. Cheers, E.J.
-
Hi PBach, I'll just give my two cents here, and I'll forward this post to some others as well -- they might want to chime in. Note that the "Bayesian ANOVA" is really a linear mixed effect model. OK: "1. Equivalence between t-tests an…
-
Thanks for reporting back, and I'm happy to hear the problem is solved! Cheers, E.J.
-
Dear JDB, Indeed we do. It will take a while before we have a complete missing data imputation procedure set up, but that's the goal. I expect this to be included within a year from now. Cheers, E.J.