EJ
About
- Username
- EJ
- Joined
- Visits
- 2,531
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
The effect size estimate under H1 would remain the same, as would the Bayes factor. The post-hoc character of the test affects only the prior model odds. Now if you wanted to obtain a model-averaged estimate of effect size using both H0 and H1, then…
-
Thanks for the reminder, I've sent another email. We will shortly be hiring new people with expertise in SEM, so then we should be able to respond to these issues faster. Cheers, E.J.
-
Hi Cathy, If your replication study is exact (so that the studies can be considered exchangeable), you can use the trick outlined in this paper: https://link.springer.com/article/10.3758/s13428-018-1092-x Cheers, E.J.
-
Hi Lotte97, I'm not 100% sure that you mean with "an assumption check", but under "Statistics" we offer "Residuals", and under "Plots" we offer "Residual Plots". Cheers, E.J.
-
Yeah we weren't really all that serious when we implemented the stars. But your suggestion does make sense I think. It would be a good feature request for our GitHub page! Cheers, E.J.
-
I'll forward this issue to our ML experts! Sorry for the tardy response. Cheers, E.J.
-
Hmm this is really a question of how you specify models in lavaan. So I would look online for lavaan documentation first. We are in the process of hiring team members with SEM expertise (our previous expert accepted a job as an assistant professor) …
-
Hello Davez, I believe that for both of these questions you are better off posting them on the JASP GitHub page, as you will have direct access to our programming team. About the spreadsheet: I suspect that you have linked a particular file type to…
-
Hi Fred, Well, this is indeed a difficult conceptual issue. The Bayesian correction for multiplicity is in the prior odds (not in the BF). When you specify these prior odds subjectively, based on background knowledge, separately for each test, then …
-
Dear User234321, Could you post this issue on our GitHub page? That gives you direct access to our Linux Guru, who is probably eager to help you. This forum is meant for discussions on the functionality of JASP. Cheers, E.J.
-
If the odds are O, the associated probability is O / (O+1). JASP gives you the BF, so you would have to multiple with the prior odds yourself. Cheers, E.J.
-
BF is a ratio, so the prior probability component needs to be in ratio form too. So you multiply BF10 with p(H1)/p(H0), which in your case equals (1-.88)/.88 = 0.136, so you get 1.703 * 0.136 = 0.232. This is the posterior odds; converting this to …
-
JASP gives you the Bayes factor (determined in part by the width of the Cauchy); this is independent of the multiplicity correction. Then, with the BF in hand, you adjust the prior odds; multiplying the BF with the prior odds yields the posterior od…
-
Hi Max, For a correction I'd recommend the procedure we use for our post-hoc ANOVA comparisons. Some background literature is cited in here: https://psyarxiv.com/s56mk Cheers, E.J.
-
Yes (you can also try it out and see). The BFexcl and BFincl do not come with this error%, but if the individual ones have small error then so will the derivatives. E.J.
-
Hi Nico, First, it is generally not a good idea to average BFs. For instance, averaging 1/3 and 3 does not yield 1. So averaging the log BFs would be better. In addition, the variability in ANOVA is quantified by a % error, which you can bring down …
-
Hi Emilie, First, you can change the measurement level by clicking the ruler icon. Second, the rule that JASP uses to guess the measurement level for ordinal vs scale variables depends on the number of different values that a variable takes on. This…
-
Hi Nik, I asked the team, and one of the members, Raoul, indicated that he had already discussed this issue with you. Is anything unclear? If you want follow-up advice it is probably best if you summarize the previous discussion first. Cheers, E.J.
-
I'll ask around. E.J.
-
Hi rooboxley, This issue seems better suited for our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/). However, I will make some inquiries. Cheers, E.J.
-
Hi jminalee, I think this is better suited for the JASP GitHub page, which brings you into contact with the programming team. I'd also include a screenshot. For details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/ Cheers, E…
-
Hi Narcilili, The Bayesian ANOVA includes a "Post-hoc Tests" section that reports the t-tests, corrected using the Westfall method (see also https://psyarxiv.com/s56mk). However, I cannot reproduce your numbers -- you have 243 whereas I ge…
-
Hi Sofia, Yes, that is the right operation. Spearman's rho operates on the ranks; it won't work for nominal variables of course. Cheers, E.J.
-
I'll pass this on. E.J.
-
Good to hear! E.J.
-
If it is not there, then it would make for a good feature request! (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) Cheers, E.J.
-
For closure: this was discussed on our GitHub page (it is scientific notation to help display very small numbers) E.J.
-
Sorry about the delay. This is strange and unusual. The programming team would need to help you out with this; you can contact them directly through our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/)…
-
I'll ask around E.J.
-
Hi Don, Those means are the model-averaged ones? E.J.