EJ
About
- Username
- EJ
- Joined
- Visits
- 2,598
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Hi Carlo, The simplest way to combine the items is to compute a sum score. You can either do this in Excel (or Calc for instance) or, in JASP, you can use our "compute column" functionality. The JASP website offers help: go to https://jasp…
-
Hi Emilie, Re. 1) You can see from the table that the summed posterior probability for the models that include the factor of interest is "1.000". In reality, that is not exactly true -- there must remain some sliver of posterior probabilit…
-
Hi Pete, First and foremost, here is a thesis that summarizes some of this work: https://psyarxiv.com/s56mk Second, I was a little confused about how many conditions you have -- you say "This means I will do 12 comparisons, 6 for the young part…
-
Hi kev_bague, JASP does not (yet) offer sequential analyses for ANOVA; the reason is that there are several BFs in play, and only one may be of interest. I guess we could show them all or ask the user to define the one that's of interest. Also, the …
-
Thanks for your question. This is a pretty general one, but I can point you to: 1. A post at https://jasp-stats.org/2018/03/20/perform-network-analysis-jasp/ 2. A video at https://www.youtube.com/watch?v=KacSF0TzoPg&feature=youtu.be I am not sur…
-
I'll ask around :-)
-
Hi TJU, The next version of JASP includes a JAGS module. For most other Bayesian analyses, we use analytic expressions (whenever we can), BAS, or BayesFactor (two R packages). These use their own sampling methods, but that's often (not always) not M…
-
Dear JDeBeer, Thanks Probably means that there are some text entries in some of the cells (e.g., "banana") and that makes it impossible, for instance, to compute a mean. Not sure -- probably the design is such that the model is not identif…
-
It means that the data are not sufficiently diagnostic for the purpose of discriminating the models -- all models retain a non-negligible amount of posterior probability. E.J.
-
Hi Gary, Here's a recent post on the topic: https://jasp-stats.org/2020/03/12/mediation-and-moderation-analysis-in-jasp/ Cheers, EJ
-
Yes, the Bayesian ANOVA can also be applied to unbalanced designs, so this should not be a problem. Cheers, EJ
-
Hi Mateus, Opinions differ. You could show them and indicate explicitly that these obtain under the assumption that there is an effect (an assumption that the data undercut). EJ
-
Ah, I see the problem. You used the first row for headings, but JASP expects data there. So instead of "V2", we want "Age", and the column needs to start with "14" E.J.
-
You need "rows fixed" then (as the rows denote the conditions) EJ
-
Suppose you want to compare two proportions. Proportion 1: 0 successes out of 5 trials Proportion 2: 1 success out of 6 trials So: Successes Failures Condition 1 0 5…
-
Update: it will be in the next release :-) E.J.
-
Yes, it would be better to be able to change it. Can you make a GitHub request, perhaps? (see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) E.J.
-
Strange! Can you send the entire JASP file so I can see what's going on? Better still, can you submit this as a GitHub issue so the programming team can have a go? Cheers, E.J.
-
I'll ask our expert! Cheers, E.J.
-
Hi Miriam, I'll ask our expert. Cheers, E.J.
-
Hi Mateus, Yes, good evidence for the null model and against the "cluster" factor E.J.
-
I'll ask our expert...maybe this was done in the developers version of JASP. E.J.
-
I don't think this is a problem. The default priors are mostly based on general desiderata, "objective-Bayes" style. For the correlation, even if the alternative hypothesis is specified to predict correlations closer to zero (this can be d…
-
Thanks. I'll ask our ANOVA expert. E.J.
-
My thoughts have not changed but also/mainly because I have not given it much thought. I will revisit this when we implement this in JASP! On our to-do list... Cheers, E.J.
-
Dear AnaOnar, There is not. JASP respects the principle of marginality, which means that if you have an interaction, the constituent main effects are in there as well. Cheers, E.J.
-
Hi Massimo, It seem to me that you have to start by computing Sensibility and Specificity for each study separately. But you need se's for this as well. I am not sure how a classical analysis deals with this (bootstrap?). I will ask our expert. Chee…
-
Hi Anna, Yes, I'm keen on that too :-) Lots of stuff happening with JASP so we have to prioritize. It will happen though. At least logistic regression is next on our list. E.J.
-
Hmmm I see our expert has not responded yet...I'll prompt him :-)
-
Hi apangallo, Descriptives is able to return the standard error, so that should help. Of course if you do a t-test you'll get the t-value as well... E.J.