EJ
About
- Username
- EJ
- Joined
- Visits
- 2,531
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
We're still working on it, and I am pinging the person responsible every time this comes up :-)
-
Hi Georges, Well you could post it here, or email some people for feedback. Cheers, E.J.
-
Hi George, About multiplicity: yes, I do think a correction is in order, unless you want to go fully subjective Bayes -- with carefully specified prior plausibilities for all hypotheses involved, there is no need for a correction. Some relevant refe…
-
Hi Martin, Thanks! There's a project ongoing in my lab where we look at the same issue (not in a state to share, but getting there). I know Joris Mulder and Florian Boing-Messing have also worked on this. Cheers, E.J.
-
Dear Narcilili, Hmm I have not given this much thought. Perhaps the authors of the BayesFactor package have done this, and I will attend them to this question. Cheers, E.J.
-
Hi Philip, Good point. I'll ask Don van den Bergh. We switched from the linear regression in the BayesFactor R package to that in the BAS R package (faster, more options -- we kept the defaults the same though). My guess is that BAS does not give an…
-
Hi dkelly84, I'll post this issue on the JASP GitHub page. Cheers, E.J.
-
Thanks. Someone (you?) also attended us to this on our GitHub page; we are fixing it. E.J.
-
Yes, that's correct. If you use ANCOVA I think it should be a fixed factor. In the future we'll try to integrate these approaches better (i.e., recognize that a binary predictor variable requires different treatment within the regression GUI) E.J.
-
Hi Ben, The easiest way is to import a .csv. So organize your spreadsheet in Excel or Calc or whatever spreadsheet editor you use, save as .csv, and import in JASP. Cheers, E.J.
-
That's correct but it does not yet include the Bayesian version
-
I'll forward this to Richard...
-
Hi Friedrich This is under development and we should have it out in the next release Cheers, E.J.
-
Hi Lior, A change from 2.5 to 12, based on about 80 additional participants, is not such a large jump. What is remarkable about this sequential plot is not the "jump", but rather the fact that up to 420 or so participants you have such sta…
-
Dear Ferengki, We offer various normality tests (depending on the analysis; more importantly, we offer QQ plots); reliability tests are in the menu (for the moment they are under Descriptives -> Reliability Analysis). What exactly do you mean wit…
-
Hi JohnAtl, We are currently working on including linear mixed models, but we're not quite there yet. With 90 trials (I assume 45 per condition), I would be amazed if your conclusions depend on the unequal data sizes. So I am going to be rebellious …
-
Hi Anna, If you have a massive BF you can tolerate a high error rate. Does it matter for your conclusions whether the BF is one trillion or two trillion in favor of the alternative hypothesis? Probably not. BFs this high will have a lot of action in…
-
interesting problem!
-
This also works for the correlation test and the AB test. E.J.
-
Hi Lior, It would be informative if you could show the sequential plot so we can assess the size of the jump; Very large jumps suggest that the observations that gave rise to it may be an outlier An evidential threshold of 3 is not a lot. Under equa…
-
I'll ask the team member who knows more about this... E.J.
-
Dear Narcilili, Yes, that's an approximation error. Note that your method works because the prior model probabilities are uniform. In general, the BF column compares the model in the top row ("0") to each of the models in the rows below (&…
-
Hi Vicente, I'm not an expert on frequentist methods for multiplicity correction. Have you Googled this? It does seem reasonable -- a little ad-hoc, but then again, it is a frequentist procedure :-) and there may be a rationale. Cheers, E.J.
-
Dear Niklas, In general, confidence intervals are numerically close to credible intervals (with a flatish prior or relatively informative data, for most models). But conceptually the procedures are very far apart. See for instance https://learnbayes…
-
I'll ask our expert...
-
Hi Anna, We have this under development at the moment! Will take a while but we are really happy with the analytical result. E.J.
-
Hi B, If your job is data management, I would stick to Excel (or OpenOffice Calc). JASP has some data editing functionality (compute columns, filtering, etc) but it is not a full-fledge editor; JASP's main strength is statistical inference. Cheers, …
-
Hi KenC, We try to avoid MCMC as much as we can. For many of our tests, we have analytic solutions, or only require a one-dimensional integral. When we do use numerical methods, the error percentage gives an indication of the accuracy of the approxi…
-
Dear Tali, Hmm, the complication here is that "N" is involved both in N-C and in IC-N. So it seems to me that you would like some kind of contrast that tests the symmetric staircase pattern against an asymmetric staircase pattern. Julia Ha…
-
Dear Philip, I guess the priors are implied. BIC is an approximation to the Bayes factor under a specific prior assumption for the model parameters (I believe a multivariate normal mean centered at the MLE but with unit information to set the prior…