EJ
About
- Username
- EJ
- Joined
- Visits
- 2,597
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Dear FrankSon, It is often not straightforward to obtain the marginal likelihood from JAGS code. When the models are nested, you could use the Savage-Dickey density ratio (e.g., http://www.ejwagenmakers.com/2010/WagenmakersEtAlCogPsy2010.pdf). There…
-
Dear Herve, That must be annoying. To fix the issue (and we really want to fix issues such as these), the programming team needs a reproducible path and as much information as you can provide (such as screenshots). Also, it would be great if you cou…
-
If you email me the file I can take a look (it only needs to have two rows or something to reproduce the issue). Alternatively, you could post this issue on our GitHub page, where you will be in direct contact with the programming team (for details …
-
This is not an explicit strategy, and moreover, I am not sure this perception is correct. For instance, the Time Series module, the Learn Stats module, the Acceptance Sampling, and the Quality Control modules are all 100% frequentist, and they have …
-
could you email me the .jasp file? EJ
-
Thanks AlejandroG, it looks like this might be very helpful EJ
-
First off, could you zoom out by pressing "control" and "minus" at the same time? (you can zoom back in with "control" and "plus"). If your items still don't show then please send a screenshot of the measureme…
-
Hello Berenike, Could you show a screenshot? Perhaps your variables are deemed nominal, and the indicated new column type is continuous? EJ
-
We have a time series module, but it only allows you to plot a single time series. This would be a good feature request for our GitHub page! EJ
-
That is really strange! We would love to understand why this happens. Is this for the current version, 0.18.1? If so, please post an issue on our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/). This …
-
Dear Roald, This may be a bug that we have already fixed. Please post such reports on out GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) as this will bring you in direct contact with the programming …
-
Another (Bayesian) approach is to use the bain module -- Herbert Hoijtink's methods explicitly take into account a combination of equality and inequality constraints. EJ
-
Also: The discrepancy is not glaring; the BF indicates anecdotal evidence, whereas the p-value is near .03, which is not that compelling The inclusion BF is based on taking all models into account, which is fundamentally different from the frequenti…
-
The mediation code is based on lavaan (so SEM), see the help file. So if you build your mediation model in SEM you should get the same result as when you use the mediation analysis. Under "options" in the mediation analysis there is a tick…
-
I guess if you analyze 10 variables you can check multivariate normality -- or if you have a partial correlation where addition of the nuisance variables gives more than two variables in your analysis. EJ
-
Hi Janet, Could you make an issue on the JASP GitHub page? This will brung you in direct contact with the programmers. For details see "How to Request a Feature or Report a Bug in JASP", https://jasp-stats.org/2018/03/29/request-feature-re…
-
The posthoc BF01, U yields 2.804*10^-4, so below 1, which means evidence in favor of H1. So BF10,U= 1/ 2.804*10^-4 = 3566.334 in favor of their being a difference. EJ
-
Hmm I am not sure we store the labels in the .csv file. A good question for the JASP GitHub page -- maybe we should also allow saving the data as an Rdata frame for instance. For details see https://jasp-stats.org/2018/03/29/request-feature-report-b…
-
I haven't seen this error before, but I do know this is an issue for our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/) -- this will bring you in direct contact with the programming team. This forum …
-
I'd like to add that there are no hard rules in statistics. There are strong recommendations at best :-) EJ
-
I haven't looked at those but I would say: inspect the data for outliers, consider transformations, and assess whether the violation is large enough to matter. Perhaps the bootstrap methodology could be of assistance as well. Cheers, E.J.
-
This would be a bug report for our GitHub page, see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/ for details. Cheers, E.J.
-
I suspect some of the packages just compute everything in logs first, and only at the very end produce a BF rather than a log BF. EJ
-
Hi IamAnna, I doubt we have this. Would be a good feature request on our GitHub page (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/). But perhaps the R console option also works -- I'll ask the team. EJ
-
This has to do with the parametrization of the models. I believe the that in the t-test the prior is on the difference between the two means, whereas in the ANOVA it is on the difference to the grand mean. You can confirm by conducting both a t-test…
-
I've asked our expert. In general, I prefer to do a Bayesian analysis in one step; that is, include the weighting and the meta-analysis simultaneously. But the two-step approach (weighting first, then Bayesian model) may be a reasonable approximatio…
-
Ah, so this is t=-4.747, and that matches with the BF10. So the problem, it seems, is that in our Bayesian post-hoc test we average across all the other factors and levels, and this is not what the frequentist test does. I'll see whether the team ha…
-
So suppose you take all of the "visual" data points, and compare it to all of the "motor" data points, collapsing across all other factors -- for that t-test, what is t and n?
-
This is a little puzzling, because the uncorrected BF ought to be just a t-test BF, and that particular t-value would not give such a huge BF (but something anecdotal in favor of H0). I've asked the team.
-
Do you have a raincloud plot of the data, showing the effect?