JohnnyB
About
 Username
 JohnnyB
 Joined
 Visits
 103
 Last Active
 Roles
 Member
Comments

Hi Kindred, From the code from the twosample ttests in JASP, I see the following: num < (ns[1]  1) * sds[1]^2 + (ns[2]  1) * sds[2]^2 sdPooled < sqrt(num / (ns[1] + ns[2]  2)) if (test == "Welch") # Use different…

Hi Manuel Yes, that is correct!

Hi Manuel, To add to what EJ said, the simple effects analysis is simply a conditional anova, with some correction for multiple comparisons (using the total sum of squares and degrees of freedom to compute the conditional F statistic). Unfortunate…

Hi Noamwe, That is an excellent suggestion, I will look into adding this to the next version of JASP. Thank you @MSB, I will use these resources for the implementation! Cheers, Johnny

Hi Chris, All JASP modules are now in separate github modules  you can see the ANOVA repository here. The R code for the simple main effects is on line 1573. The computation is a combination of emmeans and some manual computations for correcting th…

Hi tourette95, As a result of the approach used to enable Bayesian inference for the MannWhitney test, we obtain a posterior distribution for the standardized effect size cohen's d, but on the latent level. You can read more about this in the corre…

Just to confirm that EJ is right on this one =)

Hi Pchs0114, Pooling is generally done to create a slightly more powerful test. The "price" you pay for this is that you need to satisfy the assumption of equal variances across the levels of your factor. There are statistical tests for th…

Hi Robin, Im afraid I am not entirely sure how these are calculated. All I can say is that in the contrast analysis, the comparisons are conducted as one whole, which means that there are more groups being considered than just the 2 groups that are …

Hi Michael, To add to EJ's response (we are working on the mentioned project together), there are several Bayes factors to consider: The direct Bayes factor which compares 1 model against 1 model (this is what you get in the main table). The inclusi…

Hi RobinM, The contrast analysis and post hoc tests basically conduct ttests on the subsets of your data (comparing one group to another, based on 1 or more categorical variables). For an example, see the attached screenshot: https://forum.cogsci.n…

Hi Francesca, That's great to hear! This is indeed where things are not very clear, because there are basically two approaches you can use here: 1) Compare the full model to the full model without sex (as we discussed above). This gives an indicatio…

Hi Francesca, 1) Due to the algorithms used to compute these Bayes factors (there is some random sampling involved), there will be some slight fluctuations between each repeated result. The error % column in JASP gives an indication of how heavy the…

Hi Francesca, Unfortunately this behavior is no bug, but simply a consequence of having a model with 14 covariates. With this many variables, there are 2^15 = 32768 possible models to consider. When using the BayesFactor package in R to enumerate a…

Hi Tom, I suspect there is a bug in the frequentist linear regression analysis, because this particular analysis does not allow the specification of categorical predictors (and in this case just mistakenly treats it as continuous). If you want to co…

@EJ we resolved the issue over email, the issue was not the flipping, but that the test value was not taken into account (and just set to 0). The nightlies should already contain the fix, and Joris informed me that the windows nightly will be workin…

Hi Max, I fixed it and ran the correct code, see below! https://forum.cogsci.nl/uploads/706/P3XSSHS73VDU.png

Yes, something is wrong, I fixed it now. The test value was not considered correctly for the one sample wilcoxon...

Hi Max, I just looked, and the BF's I get for the onesample Wilcoxon tests seem to be in line with the frequentist and parametric results. Would you comfortable sharing your data set with me? That way I can take a closer look. You can also send it …

Hi Max, Could you rerun this with the last version of JASP (0.14)? I changed the underlying sampling algorithm, since it had a bug that would sometimes lead to very conservative results, just like you are describing. If you still have this issue ple…

Yes, the ANCOVA youtube video from the table is this one: https://www.youtube.com/watch?v=Jxrq_T8InBY&feature=youtu.be

For the ANCOVA you can specify multiple continous or factor covariates, with a single dependent variable. Maybe you are talking about MANCOVA? If so, that is not yet possible unfortunately, but it's high on my todo list!

Hi Exscistats, There is a youtube video where they do a RM ANOVA in JASP, maybe that one is useful? In the table on the page, you can find it under RM ANOVA (so not factorial RM ANOVA). Or maybe I misunderstood your question, and you have pre and p…

Hi Exscistats, You can take a look at our "How to use JASP" page, which contains links to blogposts/youtube videos/gifs that illustrate particular analyses (for example ANOVA). Cheers Johnny

Hi Rohan, I should have introduced my post by saying that I'm definitely not an expert on these post hoc corrections. What you're saying makes sense  it would be better to take into account the number of comparisons rather than the number of levels…

Hi Rohan, That's great to hear! For the calculation, you can look at this paper, pages 1315, where they coincidentally also use 4 conditions =) Cheers, Johnny

Hi Robin, Yes you are right, my apologies! Cheers Johnny

Hi Rob, Yes I think that makes sense. To illustrate, I did the 4 analyses in JASP: https://osf.io/36mxs/ It contains the frequentist anova with posttest and pretest as covariate, compared to the ANOVA with the change scores. Then I repeated it wit…

Hi Rohan, That's a good question, and not something routinely tackled by the literature. Suggestion 1) is basically doing a simple main effects analysis. Where in the frequentist framework you would correct for multiple comparisons by using a diffe…

Hi Charlotte, If I understand correctly, the Bayesian post hoc test corrects for multiplicity by adjusting the prior odds. In a normal comparison, the prior odds are set 5050, so the Bayes factor equals the posterior odds. However, if the prior odd…