vandenman
About
- Username
- vandenman
- Joined
- Visits
- 83
- Last Active
- Roles
- Member
Comments
-
Hi Narcilili, I'm assuming that you have a single linear regression model (no model-averaging). is the predicted weight loss of 3.806 the mean of a normal distribution of predicted values for this flour beetle? If it is, then how is the 95% credibl…
-
Hi bertheat, Unfortunately, I don't think it is possible to do this with the drag and drop interface right now. A workaround is to use R code, like so: dataVar <- contNormal # change this into LR Average groupVar <- facFive # change this …
-
I'm getting this figure: https://forum.cogsci.nl/uploads/796/BGDKOLWJCXD4.png did you rescale the data by 1000? The error bar are really to small to be the standard deviation (I did it on excel too..). The error bars are not standard deviations, b…
-
Indeed, there is not.
-
Hi Ferrari, Would it be possible to share the jasp file that created the descriptives plot? Without the, I'm afraid we're just shooting in the dark. Cheers, Don
-
Hi @sherloconan, The value for `iterations` includes the warmup and is used for the function posterior. The number of iterations for anovaBF/ lmBF is determined by the value for `Numerical accuracy`. Cheers, Don
-
@max_gold , The only available effect size measure for the Bayesian ANOVAs is R^2. This is computed for each model and you can obtain a model-averaged R^2. The frequentist ANOVAs provide η^2 and several other effect size measures for which we do not…
-
I'm not 100% sure I understand why the "bayesian ANCOVA does not appear to work", a JASP file (or R script) would be very helpful for me to fully understand what you're trying to do. Nevertheless, concerning Specifically why categorical va…
-
Hi Carlos_psycho, I can't seem to replicate the problem. For example, when I run a CFA the Parameter estimates table displays all factor loadings for me (Ubuntu 20.04, JASP 0.14.3): https://forum.cogsci.nl/uploads/469/U59G8PTVDBWW.png Could you po…
-
Hi! The latest version of JASP (0.14.1) does allow qnorm, so if you upgrade this error message should disappear. Hope that helps! Don
-
Hi Tali, I do get normal output (e.g., see the screenshot below): https://forum.cogsci.nl/uploads/499/4ENY0H6PL761.png if this is not the case for you, then please file a bug report at https://github.com/jasp-stats/jasp-issues/issues/new/choose. C…
-
Hi Manhervart, > I somehow thought that because of the unsupervised nature of K-means clustering I'm not allowed to use labels. In general, that's true. A t-SNE plot is a high-dimensional projection of all the variables to make the results some…
-
Hi Lone, JASP checks if the weights are within [1, Inf) and otherwise it shows an error. This is actually, a mistake, the weights are fine as long as they are within (0, Inf). We'll make sure to fix this in the next release! Cheers, Don
-
Those means are the model-averaged ones? If you selected `Model averaged` then, yes. Otherwise, it's whatever is selected in this drop down: https://forum.cogsci.nl/uploads/928/OQJIFBWAIT4H.png
-
Hi Emily, Just to make sure we're on the same page, the column "mean" of the posterior summary table shows standardized beta coefficients but you would like an option to see the unstandardized coefficients? Cheers, Don
-
Hi Andre, The nightlies are available here: https://static.jasp-stats.org/Nightlies/ and the latest nightlies should allow you to use categorical variables as covariates. If you encounter any bugs, please let us know! (See https://jasp-stats.org/20…
-
Hi dimitrib, Concerning, IIs there a way to save and applied the model to a new dataset? Or at least use it to make prediction on unclassified data added in me dataset? We're working on that. I hope that it will be in the next release, otherwise, i…
-
Previously we did allow factors to be added as predictors, but they were not analyzed as factors. That's indeed the reason why you can't add factors. In this case, the ordinal variable attract is analyzed as if it were a continuous variable. You can…
-
This is currently not possible. If you want to see this in a future version of JASP, please make a feature request at https://github.com/jasp-stats/jasp-issues. See https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/ for some more inf…
-
So the function in R that you're looking for is grepl(pattern, x) , which returns TRUE if an element of x contains the pattern (e.g., Camera). Unfortunately, this function is not in our whitelist so that won't work for now. In the meantime, you can…
-
If you go to "model" then you'll see that JASP adds all interactions effects between the fixed factors by default: https://forum.cogsci.nl/uploads/627/C1QJ7R62873I.png However, that might be a bit overdoing it for your situation. If you cl…
-
How many covariates & Fixed factors do you have? And are you using JASP 0.14.1? Something like this works for me without any problems in JASP 0.14.1: https://forum.cogsci.nl/uploads/504/D3OG3LMSYU5P.png Could you send me a screenshot of how man…
-
If I remember correctly, it's under Plots: https://forum.cogsci.nl/uploads/354/G3HDVT58TTOE.png
-
Could you perhaps share the code and/ or data you use so that we can replicate this discrepancy? In the simple example below, I get basically identical results in JASP and R. dd <- read.csv("https://raw.githubusercontent.com/jasp-stats/jasp-…
-
There's not really a tutorial out there (yet), but here goes. 1) Open the observed values tab: https://forum.cogsci.nl/uploads/099/3OYY5HBSPDAH.png 2) Click on "Add Data": https://forum.cogsci.nl/uploads/201/ZHMZQT65CZPT.png 3) In the col…
-
Hi Francesca, By default JASP enumerates all possible models. In your case with 15 predictors there are 2^15 = 32768 models. That simply takes a very long time. We will look at ways we can improve the speed and feedback (e.g., in your scenario we sh…
-
Hi Liesbeth, Can you attach one of these jasp files either here or on GitHub? If you'd rather not post the data publicly, you can also email it to d.vandenbergh at jasp-stats.org. Cheers, Don
-
Hi, Unfortunately, it's not possible to do that yet, but it's high on the priority list! Cheers, Don
-
Hi Martin, is that the "non-frequentist" R2 (i.e., the R2 considering all the models, not just the point-estimate of the best model a la frequentist R2?) Yes. The Bayesian R-squared is derived from Gelman's unpublished manuscript. So R2 is…
-
Hi, sorry for the late reply. Regularized linear regression does not allow for interaction effects at the moment. If you open a feature request at our GitHub page we'll assign it to the appropriate developer. Cheers, Don