JohnnyB
About
- Username
- JohnnyB
- Joined
- Visits
- 148
- Last Active
- Roles
- Member
Comments
-
Hi @AlessioF , When you have a balanced design, like you have in your simulated data, the types of sums of squares will yield identical results. When using the car package and using Anova, you need to also make sure the same contrasts are being used…
-
Hi @Jadran , Yes, you can take the correction factor and apply it to the df in the simple effects table, and with some extra calculations also recompute the F statistic and p-value: the Sum of squares will stay the same, but the mean square will cha…
-
Hi @JonazM, Yes, that's correct! I dont think this "within-within" is a common way of phrasing it - I would just call it a two-way (or however many predictor variables you have) RM ANOVA, or more generally a factorial RM ANOVA. In the case…
-
Hi @JonazM, I checked the book, and the table's caption indicates that it only presents incomplete data - the full data is based on 13 participants and not 4, so I don't think you can recreate the analysis results in JASP since we don't have the ful…
-
Yes, just closed the issue today: https://github.com/jasp-stats/jasp-issues/issues/2127#event-14149289225 I now made the whole normalization optional, rather than only the Morey bit of the correction (which is also consistent with the option name &q…
-
Hi @PerPalmgren , It's indeed the uncorrected p-value and then two with the corrections applied. The uncorrected p-value could be used if the comparisons are planned, rather than done exploratory. However, we could remove the uncorrected one to avoi…
-
Hi @Mirjam , As @andersony3k rightfully pointed out, there are different effect sizes at play here. The rank-biserial correlation is a correlation and is bound to be between -1 and 1, while the effect size for the Bayesian Wilcoxon is Cohen's d base…
-
Hi @Emilie_V , The option refers to the p-values only. Unfortunately CI's can only be corrected using the Bonferroni method in RM ANOVA - this is also a limitation in R, as far as I know. I did just update the helpfiles in the analysis to make this …
-
Hi @saseeri , To control for certain variables, and see if your variable of interest still adds predictive value on top of the control variables, you can do hierarchical regression, where you add the control variables to the lowest model (commonly c…
-
Hi @TarandeepKang and @MartinM , Yes, somehow this got removed at some point. I added the feature back, so it will available again in JASP 0.19 (probably released somewhere in April). Cheers, Johnny
-
Hi Carsten, Ah, sorry! Yes, the analysis in JASP matches the method described in the paper. I see now that it is not included in the citations/helpfile, so I will make sure to add it. Cheers Johnny
-
Hi Carsten, You can download JASP - the analysis from that paper is available under "T-Tests" -> "Bayesian Paired Samples T-Test" and "Bayesian One Sample T-Test", depending on your research scenario. Cheers Johnny
-
Hi @Dexterama, If you add a continuous covariate in the RM ANOVA, it will appear in the between subjects effects table, in addition to all possible interactions being added (since any interaction effect will affect the interpretation of the main eff…
-
Sorry, there were all sorts of things that popped up instead.. it's still on our radar, just not with such high priority (since we do already have Bayesian inference for a rank-based correlation coefficient in Kendall's tau). Kind regards Johnny
-
Hi @laiskl , The contrast analyses are only available as two-sided tests for now. The contrast weights determine whether you compute A-B or B-A, which in the case of a two-sided t-test leads to the same results. You could manually take the two-sided…
-
Hi @jsmnstn , JASP uses the emmeans package in R - specifically, the effect_size function. The effect sizes are therefore based on the full specified model, so might differ from when you would conduct individual t-tests. If you want, you can post/em…
-
Hi @PerPalmgren , When you only specify two variables, the two tests are equivalent - the multivariate normality (which has as many dimensions as specified variables) then becomes the bivariate normality check. I guess that when all variables are re…
-
In the meantime I doublechecked the results of JASP with the PMCMRplus package in R, and get the same results for the Conover tests - they do differ from jamovi's, since it seems they use an outdated package (PMCPR instead of PMCMRplus). Kind regar…
-
Could you share the JASP file you used? You can send it to j.b.vandoorn<at>uva.nl Without it I do not have a way to analyze your situation.
-
Hi @gvt , The friedman test is only appropriate for univariate designs, not for designs that have more than 1 predictor variables, as seems to be the case for you. I understand that makes the Friedman test fairly limited, but for now that is beyond …
-
Hi @FranckM , The box should lead to different SE's for within subjects factors - are you perhaps looking at a between subjects factor that is in your RM design? Cheers Johnny
-
Hi @kay_P & @FeB , I'll reply to each question of FeB below, because I think they also cover kay's question: Question 1: From what we were able to gather from the Internet, you can always use repeated measures in SPSS or JASP and enter a covaria…
-
Hi @EmilieC If your design is balanced (also in terms of continuous covariates), then the marginal means will be at least highly similar to the descriptive means, so then the paired t-tests will give an accurate idea of the marginal means differenc…
-
HI @EmilieC , Yes, that one is definitely related, but it's a feature, rather than a bug (and consistent with other analysis software). The blogpost I linked explains this property more clearly, including an example. Cheers Johnny
-
Hi @andersony3k , I took a look at your data files and comparison of the different programs - it seems in one you applied a filter and in one you did not, which leads to different results. Removing the filter leads to the same results, which are in …
-
Hi @EmilieC , You are right - the interactions have disappeared from the marginal means menu and we are currently working on bringing those back! There is a difference between the frequentist and Bayesian anova in how they handle the posthoc tests (…
-
Hi @MaddieP , Thanks! The JASP computation (https://github.com/jasp-stats/jaspAnova/blob/ae3f25859919c9a91a19832ae8f09065399f2c84/R/manova.R#L246) is based on the BioTools R package, but also produces the same results as the HePlots package: > he…
-
Thanks @MaddieP , what was the model you used? in terms of (in)dependent variables.
-
Hi @MaddieP, Could you please provide a data set where you obtain different results? I just checked against the heplots package (https://search.r-project.org/CRAN/refmans/heplots/html/boxM.html), and get the same results in JASP. Kind regards Johnny
-
Hi @alexa , To add to EJ's comments - I would not use too extreme values in the robustness test, since at some point the prior becomes so narrow or wide that the model just becomes non-sensical. EJ's suggestion to double and half the main values wor…