cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar

inbalanced classification option

Status: Investigating Submitted by on ‎08-23-2022 08:58 AM
3 Comments (3 New)

In medical research the outcome under study is frequently rare, so the data are highly unbalanced.

The model perfomance can significnatly improofed by correction for inbalancing by over- or undersampling. Therefore, I would suggets that all prediction model platforms should have the inbalanced classification option. Even better, the Model screening platform should have the inbalanced classification option included.

 

Regards,

 

Lu

3 Comments
Sarah-Sylvestre
Staff
Staff
‎09-21-2022 05:04 PM
‎09-21-2022 05:04 PM
Status changed to: Acknowledged

@Lu - Thank you for your suggestion! We have captured your request and will take it under consideration.

Sarah-Sylvestre
Staff
Staff
‎09-23-2022 10:55 AM
‎09-23-2022 10:55 AM
Status changed to: Investigating

@Lu -  Thank you for this suggestion, it has been submitted and is being evaluated for possible inclusion in a future release.  In the meantime, there are a few add-ins that address this that I think you are aware of.

 

https://community.jmp.com/t5/JMP-Add-Ins/Stratified-Data-Partitioning-with-balancing-options-add-in/...
https://community.jmp.com/t5/JMP-Add-Ins/Imbalanced-Classification-Add-In/ta-p/304836

 

Sarah-Sylvestre
Staff
Staff
‎09-23-2022 10:57 AM
‎09-23-2022 10:57 AM

@Lu - Also, Decision threshold enables you to change the cutoff for classification with unbalanced data in JMP 16.  It is available in most modeling platforms for binary response.