JMP Academic Webinar - Teaching Design of Experiments with JMP

@cedrick07, Taguchi designs typically target only a single response, and JMP's Taguchi Array allows only one response. You could try creating a composite response, using some function (a weighted average, for example) to meaningfully combine all your responses into one. You also could use a multi-objective optimization approach, where you collect all responses, then analyze each separately in Fit Model, then use the general Profiler under the Graph menu to perform a tradeoff analysis.

Taguchi designs have fallen out of favor with many statisticians. If you are considering Taguchi designs because you need to optimize the within-specification rate in the presence of noise factors, you could consider running another type of design that supports multiple responses (perhaps a Custom Design), manipulating both the noise and control factors as in a Taguchi desing, and then using a simulation experiment to identify optimal settings given inherent variation in the noise factors. See this video for more information on this approach: https://community.jmp.com/t5/JMP-On-Air/Simulation-Experiment/ta-p/261021.

If you are on a limited budget, you should consider the Custom Designer, which will provide the optimal design given restrictions you place on the run size (among other design parameters). It easily accommodates multiple responses.

You might work through the DOE Intro Kit to get familiar with the Custom Designer, and then view one or more Mastering JMP webinars on DOE to learn more of the details. If you have further questions to pose to the JMP User Community, I recommend posting them to the general discussion board.

You'd first want to determine whether creating a composite response makes sense conceptually. It may be the case that the individual responses cannot be combined mathematically in a meaningful way. But if you do determine a meaningful way to combine them, you could use JMP's Formula Editor to create the formula to calculate the composite response. You would use that formula in the response column of your Taguchi design table.