vandenman
About
- Username
- vandenman
- Joined
- Visits
- 77
- Last Active
- Roles
- Member
Comments
-
Hi Marissa, If you change the data type from scale to ordinal or nominal then the x-axis reflects the discrete nature of the data: https://forum.cogsci.nl/uploads/030/GWZY9P6U5AMR.png You can click the icon next to the column name to change the typ…
-
That's expected shrinkage due to both the parameter prior and the model prior. If you pick the priors "just right" then you can make the two approaches produce more or less identical results: https://forum.cogsci.nl/uploads/090/PH9ICRVH7P7…
-
Hi Nitzan, The Bayesian model uses a centered design matrix. So rather than y ~ intercept + b*x it does y ~ intercept * b * (x - mean(x)). This does not affect statistical significance but it does change the interpretation of the parameters. Specif…
-
Hi Quinnculver, This is indeed not possible at the moment. If you would like to see this at some point in the future, please create a feature request at https://github.com/jasp-stats/jasp-issues/issues?q=sort%3Aupdated-desc+is%3Aissue+is%3Aopen (se…
-
Hi PerPalmgren, If you have a column with the correlations you can create a new column that computes the z-scores from the correlations like so: https://forum.cogsci.nl/uploads/921/1DP0HOQSNWL4.png or with R code like so https://forum.cogsci.nl/upl…
-
Hi, The prior we use in logistic regression is based Li & Clyde (2018). There is not really a notion of non-informativeness for the priors in logistic regression. Instead, other properties are examined (e.g., model selection consistency), see s…
-
Hi, What happens is that The data are bootstrapped A network analysis is conducted on each bootstrapped sample For each bootstrapped analysis, the difference between the edges weights (or centrality measures) is computed. Those form a distribution,…
-
Hi n00025927, Currently, this cannot be done with Jasp and you'd have to use R to compare the two network, with the R package NetworkComparisonTest. You can try to compare the two networks you have substantially, but it will be difficult to say some…
-
Hi MB, The values are normalized by subtracting the mean and dividing by the standard deviation (i.e., they are z-scores). So there is no need for them to lie between 0 and 1. Hope that helps, Don
-
Hi, I do not believe this will work, nor are the steps you list necessary (e.g., JAGS is shipped with JASP already, there is no need to install it additionally and any separately installed JAGS will never be used). Could you provide more informatio…
-
Hi MaliAS, Have you tried increasing the numerical accuracy, or switching to the Laplace approximation? The error % in your results is rather large and differs between the two runs. This could very well explain the difference in the results between…
-
The maximum value of 64-bit float is 2^1024 * (1-2^(-53)) ~ 1.797693e+308. So I guess it would be fine to write BF > 2^2^10. However, the log Bayes factor tends to overflow to infinity more slowly, so perhaps it's better to report that one instea…
-
Hi, Would a filter like the one below work? https://forum.cogsci.nl/uploads/489/G5KYPVNEEL1F.png This excludes participants that have one or more NAs in the items. If you want to exclude them only if all values are missing, then change the | to a …
-
Hi TJ, Thanks for bringing this up. Your report is spot on, we're using the same input field for the g of the g-prior and the alpha for the hyper-g priors. However, this is indeed overly restrictive. I'll update this for the next release so that th…
-
Hi Paul, Right now there is no built-in way to do this. You could create a new variable that is an interaction of the two independent variables and then use that as a grouping variable in descriptives. Alternatively, you could look at the descripti…
-
But, now, I need those numbers to be transformed into a categorical variable where 3,4,5 means NonLonely and 7,8,9 means Severely Lonely. This means skipping the scores that are a 6 as I need to go for the extremes for the second round of ANOVAs (re…
-
That's a good point. But how exactly that is implemented is specific to the method that is used. For example, in Bayesian linear regression, we automatically account for model complexity. In the frequentist counterpart, however, we would indeed need…
-
There is no good support for polynomial regression yet, but you could use computed columns to manually create variables raised to a power and then include those in the analyses. This means the polynomials are not orthogonal, but if the order is not …
-
Well, the drag and drop is under the hood translated to R code. If you want, this can be shown to you. In R, many operations (e.g., +, -, *, /) are vectorized if the vectors have the same length. For example, you can add two vectors. So to compute t…
-
I'm not sure what jamovi does, but in R we simply execute the R code and try to use the return value. So if this is the dataset loaded in JASP: mydata = data.frame( person = c(1, 2, 3), q = c(10, 100, 1000), r = c(20, NA, 2000), s = c(30,…
-
Hi Ananda, You could create multiple computed columns, one for each new variable you want. If that is not what you meant, could you provide an example? Best, Don
-
Hi Johan, Sorry for the tardy reply, I looked into what was going on here, but promptly forgot to leave a message. The CIs in the plots account for differences in within and between factors. The descriptives table, however, does not take this into …
-
This should be fixed in the upcoming release, a pull request was just merged that corrected this bug.
-
Hi Mircea, That indeed looks like a bug, thanks for bringing it to our attention! I will keep you posted when it is resolved. Don
-
Hi Berenike, You can do this with a computed column and the ifElse function. https://forum.cogsci.nl/uploads/603/X31PP1I2OWPL.png Note that for the condition (the first argument to ifElse), you must first drag the comparison operator (for example, …
-
Hi Per, No worries! The key is to realize that the two statements are nested, so it is actually one statement like so: ifElse(facFive <= 2, 1, ifElse(facFive <= 3, 2, 3)) We can also see this as a decision tree, like below: https://forum.cogs…
-
Hi, As far as I know, it's only possible to use LaTeX in annotations, e.g., here: https://forum.cogsci.nl/uploads/402/ZEAHP4JIG52V.png you could try subscripts that are supported by Unicode (see https://en.wikipedia.org/wiki/Unicode_subscripts_and…
-
Hi, The mode is currently computed as if all variables are continuous. This is a mistake and will be fixed in the next version of JASP, where it will be computed differently for ordinal and nominal data. Cheers, Don
-
No worries, you can do it like so with the GUI: https://forum.cogsci.nl/uploads/254/N7FRO0B8YFOQ.png But if you ever have many more categories the nested ifelse statements might become a bit cumbersome. You can also write R code directly if you clic…
-
Hi! How about this? https://forum.cogsci.nl/uploads/166/JV7GLG8J02BU.png If "Other" always has the same capitalization then this should work. Otherwise, it's also possible to use nested `ifElse` statements, but that becomes a bit messy. Le…