EJ
About
- Username
- EJ
- Joined
- Visits
- 2,440
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Yes, doubling and halving is a fair strategy. Not sure why BSEM would differ, other than updates in the underlying R package (I will ask Julius to check) EJ
-
Hello JNL, Yes You can check out some of the RM ANOVA examples in the JASP data library, the online data library, or the examples from the Field course book "Discovering Statistics Using JASP" -- see the Teaching menu on the JASP website. …
-
Also, you want to select "best model on top" instead of "null model on top" so that the results are a little easier to interpret. And in general I would say the results concerning the interaction suggest "absence of evidence…
-
Hi Franzis, These technical problems are best dealt with through GitHub, which brings you in direct contact with the programming team (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) Your issue has been reported …
-
Hello Chris, Thanks for bringing this up. Could you post this on our GitHub page? This is a technical question and you are better off talking to the programming team directly. For details see https://jasp-stats.org/2018/03/29/request-feature-report-…
-
Also, you might try getting rid of spaces and underscores in variable names...
-
A screenshot and the model code would help!
-
(and I have made an issue on our internal JASP issue tracker, thanks for reporting this!)
-
I agree the order is strange, and we ought to fix that.
-
I don't think we have this at the moment, but it would be a great feature request for our GitHub page -- for details see https://jasp-stats.org/feature-requests-bug-reports/ EJ
-
There are a number of new modules that needed thorough testing and bug fixing. But there are architectural changes as well (to improve the data editing for instance, and to enhance security by sandboxing). If we only released for Linux then life wo…
-
We hope for this week or next week
-
Hi Mat, The unequal model priors are based on the beta-binomial setup. It can be conceptualized as follows: first, equal prior probability is assigned to each model class (i.e., the class of models with no predictors, the class of models with one pr…
-
[I never said this, but for quick help just try ChatGPT]
-
Or use control+ or control- to zoom in and out EJ
-
Hmm I think this is something for a bug report on our GitHub page -- see https://jasp-stats.org/feature-requests-bug-reports/ for details Cheers, E.J.
-
We are testing it now, and hope to have it ready before the start of our workshop week (https://jasp-stats.org/workshops/) EJ
-
Seems reasonable, but when in doubt conduct a sensitivity analysis EJ
-
Hi Eva, Have you computed the same result in a different program (R?). You can also give ChatGPT a shot. If you can't get to the bottom of this please provide a concrete data set so it is easier to discuss the matter. Cheers, E.J.
-
This has been known to happen when .jasp files grow very large and contain very many analyses -- it then becomes an issue of system resources. I strongly recommend the GitHub route! Keep us posted how you are doing please. EJ
-
That is an interesting thought! Of course the ranks are consistent with any monotonic increase (not just linear) but that might actually be a good idea in this case -- it is clear that the trend cannot be linear on the original scale, so it makes se…
-
Do you have a concrete example, possible urls, and an existing R package in mind? EJ
-
The analysis demands that the variables are scale, not ordinal -- the star next to the ruler icon indicates that they are treated as scale to make the analysis possible.
-
There is --all code is open-source-- but when the R button is absent is will be similar to an archeological expedition on GitHub. I recommend that you issue a feature request asking for all code to have the R button.
-
I'll forward this to our expert. I think it is a known bug! EJ
-
I will forward this to the experts. If we mention it in the helpfile and it is missing it might be an oversight and you could issue a bug report on our GitHub page (https://jasp-stats.org/feature-requests-bug-reports/) EJ
-
Hi Vinschger: Exactly. If you treat them as scale variables the analysis is much simpler. Otherwise you have to use ordinal analyses, which are less developed. Luckily people often analyze the mean across several Likert scales, which behaves more li…
-
Definitely!
-
This is an issue is for the JASP GitHub page, which will bring you in direct contact with the programming team (for details see https://jasp-stats.org/feature-requests-bug-reports/) Cheers, E.J.
-
I am not sure JASP can handle censoring in its regression routines (my currenty guess is that it cannot). You might want to issue a feature request on our GitHub page -- see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/ Cheers, …