EJ
About
- Username
- EJ
- Joined
- Visits
- 2,559
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Hi C_B_Prof, Check out the "Descriptives" -- first tab on the ribbon. JASP does not do data-editing yet, but it's in the works. Cheers, E.J.
-
Yes and yes. Also, we are working to include nonparametric Bayesian tests. Cheers, E.J.
-
Ah yes. Well that requires a separate development. You could plot the two posteriors and eyeball them, but that is not a real test. We have it on our radar but it will take some time to get done. E.J.
-
Hi Ether, Really, this is not a problem. We do not make any of these changes. However, if you want to discuss this with our programming team, you can create an issue on GitHub (see the link on https://jasp-stats.org/feature-requests/). You have to …
-
First, Richard Morey and Jeff Rouder have a paper on BF meta-analyses (2011 in PBR, a response to Bem). Second, are you interested in a BF for the difference in correlations? E.J.
-
Thanks, I'll pass this on. EJ.
-
Hi Ether, You are not supposed to peek inside the exe! :-) To clarify: JASP uses R (and specific R packages) under the hood, so we need to bundle it together with the GUI routines. The JASP installation happens in a way so that it does not interfer…
-
Either that, or refer to the default and cite the BayesFactor package documentation for details. E.J.
-
If you've got a variable "time" ("1", "2", "3", say) and you pick split by "time", then it should work. But it is difficult to convey these things without the benefit of a drawing, so maybe I misunde…
-
Hi Sarah, The box plot is a recent addition and we are still working out ways to extend it. That error message sounds like it might be a bug though (different numbers of response should not be a problem) -- can you report it on the JASP GitHub page…
-
When you set the "samples" function to manual and you increase the default number (which is what "auto" does -- I guess we could have called it "default") then you can decrease the %error in the estimation of your BFs. …
-
Hi Daniel, Yes, that is correct: for the BF and the posterior distribution, r and N alone are sufficient. See http://arxiv.org/abs/1510.01188 for details. As far as the quantitative meta-analysis is concerned, I'd prefer to see all of the BFs; usi…
-
It appears to me as if you wish to do a comparison of two multinomials. There is one multinomial per group, and each multinomial has the disease categories. So it looks as if you need the contingency table functionality. Cheers, E.J.
-
You can send it to jasp.stats@gmail.com
-
My solution is to give the variables really short names :-) I'll pass this on to the programmers. E.J.
-
Hi MSB, The model formulation is different. The regression model is based on the Jeffreys-Zellner-Siow framework, and the correlation model is based on the initial proposal by Jeffreys. The paper by Ruud Wetzels presents a correlation in line with …
-
Hi Rex, This is weird. JASP uses standard procedures to guess the measurement level. Can you send the offending csv file? E.J.
-
Maybe an upside-down cross?
-
Hi Sanne, We use code from R packages, and most of the time SPSS is wrong and R is right, but who knows, this may be an exception. Can you provide more specifics so we can look into it? Cheers, E.J.
-
Interesting stuff! (and yes I did mean to hint at the fatter tails). Cheers, E.J.
-
Hi RA, I am working on a JASP manual, and on a JASP article that describes how to interpret the JASP output for ANOVA designs. You can also check out the ANOVA paper on my website, http://www.ejwagenmakers.com/inpress/RouderEtAlinpressANOVAPM.pdf …
-
We are about to submit the revision. We will post the paper as soon as it's accepted. Cheers, E.J.
-
Hi kldavids, Sorry for the tardy response -- somehow your post didn't prompt me to respond immediately. I do recall fielding an "El Capitan" question before. So I hope the issue has already been solved. If you want the attention of the JA…
-
Hi Papi, This is an interesting approach. I think Jeffreys (1961) also discusses the comparison between two correlations, but I might misremember. Your approach assumes that "q" captures the relevant information in the data -- to the exte…
-
Hi Matt, I'll look into this. Basically we use R, but I'll ask the person who coded this to look into this issue specifically. Thanks for pointing it out. Cheers, E.J.
-
Hi ESV, Yes, when you design them as nuisance they get added as covariates. This is indeed similar to a hierarchical analyses where you add batches of covariates in a particular order. Cheers, E.J.
-
Hi Simon, I'm working on a JASP manual and it will have sections "Example Report". Until that's finished, your best bet is to look at papers that already report Bayesian analyses (such as my own; see my website :-)). Cheers, E.J.
-
The paper has a "minor revision from The American Statistician. We've almost completed the revision and I'm pretty confident. But you never know.
-
Hi Pat, I've asked the JASP programmers what's up. In the mean time I'd encourage you to post bug reports on the JASP GitHub page -- this is the page that the programmers check. Also, it is the page that most users would consult in case they encoun…
-
Hi Tom, Well, if you look at BF10, you see that for every model you have strong evidence in its favor compared to the model without any factors. The full model that includes the interaction is supported (versus the null) more than the model with th…