[Bug]: ML Regression-Random Forest results depend on order of predictors?

[EJWagenmakers]

JASP Version

0.95.2

Commit ID

No response

JASP Module

Machine Learning

What analysis are you seeing the problem on?

Regression-Random Forest

What OS are you seeing the problem on?

Windows 11

Bug Description

A user demonstrated that the results from Regression-Random Forest seem to depend on the order of the predictors in the variable input field. It was an example with relatively few observations and 10 or so predictors. Moving the order around seems to yield a qualitatively different outcome?

Expected Behaviour

The dependence on the order would be undesirable. Is this expected to happen?

Steps to Reproduce

I have not tried to reproduce this, but it should be easy to check. (you would need to untick the seed to see assess the variability)

Log (if any)

No response

More Debug Information

No response

Final Checklist

• I have included a screenshot showcasing the issue, if possible.
• I have included a JASP file (zipped) or data file that causes the crash/bug, if applicable.
• I have accurately described the bug, and steps to reproduce it.

[github-actions]

@EJWagenmakers, thanks for taking the time to create this issue. If possible (and applicable), please upload to the issue website (#3712, attaching to an email does not work) a screenshot showcasing the problem, and/or a compressed (zipped) .jasp file or the data file that causes the issue. If you would prefer not to make your data publicly available, you can send your file(s) directly to us, issues@jasp-stats.org

[koenderks]

Doesn't unticking the seed make it logical that the results differ each time and with differentpy ordered predictors? It seems like you would neet to fix the seed and then check if the results differ for differentpy ordered predictors. I'll try when I have time

[EJWagenmakers]

Well I can imagine that changing the order of predictors does something to how the randomness is being used, effectively changing the seed. So I would untick the seed and compare the variability and mean results to that with a different order of variables