EJ
About
- Username
- EJ
- Joined
- Visits
- 2,598
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
JASP uses an R package for this, must be the settings that make the difference. I'll ask Johnny to look into this.
-
Yes, Johnny will look into it when he returns from a conference and we'll update you on our progress. E.J.
-
OK, based on some quick research by Johnny van Doorn, it appears that the formula is in need of correction when there are within-subject factors. This is a good catch. We'll fix this in our upcoming release. Cheers, E.J.
-
Definitely! We are working to develop and include analysis methods based on ranks -- these methods naturally make assumptions that are much weaker. E.J.
-
Hmm. Let me ask a team member and get back to you. E.J.
-
Dear startfromzero, I believe that the Bayesian ANOVA does make assumptions, for instance about homogeneity of variance. This is similar to the Bayesian t-test that assumes a common sigma. One may develop a Bayesian Welch test (with two sigma's, on…
-
The next JASP version will present to options for "Analysis of Effects", namely "across all models" and "across matched models" -- the second one is Baws ;-)
-
I'd say you interpret the interaction, as you propose. JASP respect the principle of marginality, so models with the interaction automatically also include the constituent main effects. E.J.
-
Hi Eniseg2, Well, the model with the interaction is preferred over the other models. Compared to the model with only Season, the BF = 870/190 = 4.58. Maybe it also helps to select "Compare to best model" and set the Bayes factor display t…
-
BF simply quantities the evidence. On average, more participants means more evidence, but it is possible to obtain decisive evidence with few observations. The sequential analysis shows the evidential flow as the sample grows. E.J.
-
Hi metamorphose42, Yes, you can use BFs. Opinions differ on what to make of this in case of multiple comparisons. I personally am in the Jeffreys, Scott & Berger camp, who argue that you ought to adjust your prior odds. Basically, they argue, i…
-
Hi Julian, This issue is best dealt with on our GitHub page, so you can talk to the programmers directly. They will probably want to see your file too. Cheers, E.J.
-
From JASP guru Bruno Boutin: "Sebastian is correct. On Ubuntu we use the existing R packages".
-
I'm sure this will take some more time. I'll make an inquiry as to the current state of play. E.J.
-
Ah, let me ask the team. E.J.
-
Nope it won't interfere E.J.
-
Hi Mieke, This is not (yet) possible in JASP, unfortunately. It is an important analysis. E.J.
-
For an interpretation of the strength of evidence that a Bayes factor provides, see the cartoon here: https://osf.io/3acm7/
-
Dear biopsy, The analysis assumes that the order with which the data arrive is given by the order of the rows. So the analysis is executed on the first n rows, where n is increased until the last row has been reached. The order with which the data …
-
Dear FLPS, The interpretation is straightforward: nothing much is going on. The error % provides an indication of the numerical error of approximation relative to the size of what is estimated. The BF_M term compares prior model odds (0.063/(1-0.063…
-
Dear HTIDCam, It might help us if you add the .jasp file and/or a screenshot of the error message. I will bring this to the attention of one of our team members. Usually Johnny would handle this but he's on vacation, so you might have to wait a few…
-
Hi isakohrlund, From the perspective of Miller & Chapman, the problem cannot be overcome -- it is an inherent confound. I believe Pearl had a different opinion, but there's no easy fix. So at the very least it's prudent to issue a caveat emptor…
-
Hi Isak, JASP assumes that every subject/unit is a row. So it assumes a "wide" format, not a "long" format. I've suggested on GitHub that we increase the priority level of including support for the "long" format. The wa…
-
We're working on it (or I should say, a student is working on it :-)) E.J.
-
Hi mrdata2017, I am not 100% sure I understand the question, but if you double-click on the csv data, your favorite csv editor will open -- just create a fourth column that equals the sum of the first three, press "save", and the JASP data…
-
Yes, I think you're spot on. Cheers, E.J.
-
Susanne, on GitHub you said that you resolved the issue. What was the cause of the discrepancy? Cheers, E.J.
-
Hi Bill, Thanks. I will look into it, but I can already tell you that this will most likely be an issue with an R package. E.J.
-
Courtesy of Erik-Jan van Kesteren, the underlying R code: v <- plotDat[plotDat$group == level,]$yquantiles <- quantile(v, probs=c(0.25,0.75))IQR <- quantiles[2]-quantiles[1]plotDat[plotDat$group == level,]$outlier <- v < (quantiles…
-
I am not sure what outputs to compare, exactly, but I googled this problem and it has been noted a few times before. From what I see, most of the time the issue is rounding (!). For instance see https://stats.stackexchange.com/questions/113314/spss-…