EJ
About
- Username
- EJ
- Joined
- Visits
- 2,001
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Hmm I am not sure we offer this at the moment. If you post the request on our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) it would be much appreciated. Cheers, E.J.
-
OK, so a lot of suggestions are here: https://jasp-stats.org/2022/02/22/latent-growth-curve-modeling-lgcm-in-jasp/ Effect sizes should be evident from the parameter estimates and R^2 stats it seems to be. Model fit I would assess visually (by plotti…
-
Thanks Giray, I'm looking in to who can best help you. The best check imo is to explore possible structure in the residuals. But I'll take a look. EJ
-
Thanks for this detailed report. I've notified the team and we'll respond shortly (I hope :-)) EJ
-
Hi Nathalie, The issue is that the prior structure on the regression coefficients is of a particular form that assumes the predictors are continuous. Making the methodology work for all kinds of predictors would be very interesting. I would be tempt…
-
This was addresses on GitHub; in the next version we will (hopefully) allow users to switch between normalized and non-nonmalized MSE. EJ
-
Well there are several issues here. First, the Bayesian models by default enforce the "principle of marginality", which means that when interactions are included, so are the constituent main effects. You can turn off this behavior under &q…
-
Sounds like an issue for our GitHub page! (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) EJ
-
I should think this is explained in the articles referenced at the end of the help file? EJ
-
With multiple comparisons I personally would adjust the BF threshold that signals when sufficient evidence for H1 has accrued. This will mean that the thresholds become asymmetric, because the BF one for H0 can remain the same. EJ
-
Strange. I recommend taking these issues to our GiHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) EJ
-
Add a filter that only leaves the two factors you would wish to test. Or do an ANOVA and consider the post-hoc t-test for each of the pairwise comparisons. Cheers, E.J.
-
Update: I have created some random data to yield the specific t-value, and when I run the two tests in JASP I get the same result. So it is somewhat mysterious why you find a difference. Maybe we can figure it out if you have the data. EJ
-
Hi Jon, This is puzzling! I confirmed the output from the Summary Stats module. The result from R seems wrong, because the result is so overwhelming -- are you sure you ran a paired t-test? Could you perhaps share the data and the R code? Also, I ne…
-
I've forwarded this to our expert EJ
-
Ah. Well the posterior distribution for the correlation coefficient is analytic (see https://onlinelibrary.wiley.com/doi/epdf/10.1111/stan.12111) but I don't think it is easy in JASP to get that information -- it would be a good feature request for …
-
That is extra strange, and provided additional motivation to fix this :-). I've attended the team to the issue. EJ
-
I asked the team! EJ
-
We're happy to include new functionality, but I know nothing about qualitative analyses. I had always understood it was based on the interpretation of interviews and such....OK, I did a search and found an overview video: https://www.youtube.com/wat…
-
I'll ask the team
-
Dear Johan, Let me go over your questions one by one: >First of all, I'm well aware that the methods are different and therefore not necessarily comparable, but the results shouldn't be opposed in the majority of cases, otherwise there would be p…
-
Let me get this straight. So you have a 3x3x2 RM ANOVA: "my goal is to investigate the role of different sleep measures on skin conductance responses (DV) in a fear conditioning paradigm. IVs are Conditioned Stimulus (CS, 3 levels), Context (3 …
-
This topic is discussed in a recent special issue, see https://link.springer.com/article/10.1007/s42113-021-00113-2 for the introductory paper. My own preference would be not to make an all or none choice, but model-average across all relevant model…
-
Strange. The complete model can take a long time to run since we added the random effects. Under "additional options" you coulsd try the Laplace approximation -- does this work? Otherwise I would recommend to take this to our GitHub page (…
-
Probably best to discuss this on GitHub? EJ
-
I've asked the team for support. EJ
-
Thanks, this is now taken to https://github.com/jasp-stats/jasp-issues/issues/2603 EJ
-
Hi Lena, This output does look strange: two estimates of 0 (with standard error 0), and two other estimates that both equal 0.027 (with the same standard error, 0.015). I am not sure what you mean with "selectivity", but this issue stands …
-
Dear Johan, The figure is not so relevant since it maps the empirical function from effect size to Bayes factors. For your effect size question I've notified the team... Cheers, E.J.