nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

Functional Data Explorer - How can I match two (or more) functional responses simultaneously

kpgallagher_ppg

I see how to use the FDE when I have a DOE with a functional response and want to determine how to set my DOE x's to minimize the difference in the response function to a target function (desirability function tools used).

How can this be extended so that two separate response functions can be modeled and used to select the optimum DOE settings to minimize the difference in both functional responses relative to each of their targets?

I would prefer an interactive explanation.

Example from JMP sample data

Accepted answers

Mark_Bailey

Can you create a difference column with a desirability function for minimize? That is, save the FPCs and the supplementary variables for each functional response, use a column formula to compute the difference in FPCs, and then use Graph > Profiler with the option to use original factors?

All comments

Mark_Bailey

statman

Is there any relationship between the two functional responses? Have you done Multivariate>Multivariate analysis of the multiple response functions?

kpgallagher_ppg

Yes, this is always a good approach. In the Mill Data example, there is a relationship. I was thinking of a case where there is not a strong relationship between the two functions but getting a formulation that matches both functions would be desirable.