EJ
About
- Username
- EJ
- Joined
- Visits
- 2,530
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
I am not sure whether this issue has resolved itself, but This is (or was?) valuable information for our programmers, whom you can best reach through our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/…
-
It would be a good feature request for our GitHub page! (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) However, we do offer the Amaroso distribution, and this nests a fairly large number of simpler models -- I w…
-
I've forwarded this to our expert! E.J.
-
I don't think this is a known issue, and we'd love to fix it -- thanks for bringing this to our attention. Could you make an issue on our GitHub page? (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) This needs a …
-
I suspect it is the long vs wide format (just a guess). Have you gone to the JASP Data Library and looked at the way we code other ANOVA analyses? E.J.
-
I would add that the team is eager to solve problems like these! But the best way to contact them is through our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/). This Forum is meant for interpretation…
-
I'll ask our expert. Sorry for the tardy response, I stopped getting emails from the Forum for some reason.
-
Well, there has been a big change in our RM BANOVA, so you should definitely upgrade to the latest version. See for instance https://jasp-stats.org/2022/07/29/bayesian-repeated-measures-anova-an-updated-methodology-implemented-in-jasp/ Cheers, E.J.
-
Good suggestion -- because if the scale is text, this cannot be changed to anything else (for good reason).
-
You've set a pretty narrow prior here, and nevertheless you have quite some evidence for H0. This suggests that the data show a pattern that is actually opposite the one predicted by H+. It may help to look at the descriptives (raincloud plot for in…
-
I passed this on to our expert
-
But the prior structure differs depending on the scale (continuous vs nominal) EJ
-
To the extent that the categorical variable "looks like" a scale variable, this will work. For instance, scores on an IQ test are not really continuous (they are integers), but we always treat them as such. The main problem is with nominal…
-
Not yet, but it is under development. I will let our expert know that you are eagerly awaiting this functionality :-) E.J.
-
Strange. Could you let the team know on GitHub? E.J.
-
I would start with the help file and the references therein. Also, I am sure the various YouTube videos cover this...let me look...yes, just go to YouTube and search for "factor analysis in JASP" Cheers, E.J.
-
It is under Regression -> "Generalized Linear model" E.J.
-
The module settings are reactivated when you restart JASP. So if you have the "Power" module activated on the ribbon, and you close and restart JASP, the "Power" module should still be present on the ribbon. Cheers, E.J.
-
Dear Grzegorz, In this case, isn't the design effectively a one-way ANOVA? And we do offer eta^2 for those designs... Cheers, E.J.
-
Or maybe this is the same as https://forum.cogsci.nl/discussion/8607/nominal-by-continuous-variable-crosstab-eta-in-jasp#latest -- let continue the discussion there
-
Dear Stan, Could you be a bit more specific? If you refer to the effect size measure, the eta is generally used in ANOVA designs, and we offer it there. Are you referring to something else? In this case a link to an existing procedure in R and in SP…
-
I've asked our expert! EJ
-
Hi Daiichiro, I am not sure where I can find this data set in the JASP Data Library -- can you tell me where exactly it is? E.J.
-
Hmm. Could you attach an example with concrete data? JASP uses R under the hood -- have you looked to see whether the common procedure in R gives a different result from SPSS? EJ
-
+1
-
Thanks for reporting this -- I'll forward this to our expert. It would be very helpful if you could add a screenshot, by the way! What could be the case (you could check) is that the new version uses the beta-binomial prior model specification (I th…
-
Addendum: but it would be a good idea to develop this functionality in the future! EJ
-
JASP assumes that numbers with decimals are not ordinal. How did you get the decimals into your ordinal data? I suspect that you are averaging Likert scores? -- averaging is an operation that is not meaningful for ordinal data (but of course we do i…
-
Thanks for reporting this, by the way
-
This appears to be a bug. I'll create a GitHub issue for it. E.J.