DOE custom design factor combinations

[#1]

I am designing an experiment (2 level DOE) where my factors come from two sources, an incubator that has 4 factors to be controlled and shake flasks with 3 factors. I have 3 incubators and each one can hold 12 shake flasks. I want to implement a design where the shake flask settings (12 shake flasks each with different settings) are the same for each incubator setting. Is this possible in jmp?

[#2 · Accepted solution]

When you define the factors, change the Changes setting from Easy to Hard for the factors around the incubator.

[#3]

You can replicate the runs over the three incubators, from a DOE point of view it would be less efficient (you use more runs than strictly necessary), compared to considering 8 independent factors, incubator entity being one of those.
I can imagine you may have practical reasons to do the same thing on each incubator. In these situations, I like to construct a DOE table and use the "Evaluate Design" feature. The platform already provides comparison to full factorial design, I always look at "fractional increase of confidence interval". You can also compare to other scenarios, e.g., a D-optimal design with the same number of runs.