cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
0 Kudos

Conditionnal factors

What inspired this wish list request? 

We often deal with multi-step process optimization problems. For each step it is possible to use different technologies that have different factors or to simply bypass a step.
In the diagram below, the first step can be avoided. In this case (Step 1 == "None"), it is imperative that the answer does not depend on solvent, time or temperature. For the second step, the Power must not influence the response if Step 2 == "A" (respectively for Mixing and Step 2 == "B").
This same kind of situation can be found in the case where we want to optimize both the quantity and the type of an ingredient (see https://community.jmp.com/t5/Discussions/How-do-I-indicate-that-a-mixture-factor-can-take-a-number-o...)

 

 

 

Florent_M_0-1679496515445.png

Florent_M_1-1679496759630.png

 

 

 

What is the improvement you would like to see? 

The ideal would be if JMP allows to specify "conditionnal factors" when setting a model both in the DoE and Fit Model plateform. It could be similar to nested factors.

 

Why is this idea important? 

Dealing with this kind of constraint could be done using a specific coding. That would avoid the user to implement the tricky solution proposed in the post quoted above.