Hi, it depends on your objective. If your aim is to draw conclusions about a treatment’s effectiveness wrt/ some desired outcome, you would need to compare it against a control group. For example, randomized controlled trials facilitate comparing average treatment effects between treatment group and control group units.

On the other hand, if you are less interested in policy evaluation, but want to detect hidden patterns among treatment group units, for example, you only require treatment group data. To this end, you may want to consider unsupervised learning approaches. Of course, the latter goal implies dropping (potentially large amounts of) valuable control group data.

Dear Robin M. Gubela,

You can use cgdelete or cgcreate to remove cgroups. please see following link :

https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/6/html/resource_management_guide/sec-removing_cgroups

Also i suggest you to see links on subject.

https://man7.org/linux/man-pages/man7/cgroups.7.html

https://experienceleague.adobe.com/docs/data-workbench/using/admin/user-groups/t-removing-a-user-group.html?lang=en

https://docs.microsoft.com/en-us/dotnet/desktop/winforms/controls/how-to-add-to-or-remove-from-a-collection-of-controls-at-run-time?view=netframeworkdesktop-4.8

Best regards

please see the following links of similar discussion.

1. https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/6/html/resource_management_guide/sec-removing_cgroups

2. https://www.researchgate.net/post/How_can_we_remove_the_effect_of_different_factors_to_see_the_single_factor_effect_in_a_study_of_BMI