For our work with transfection processes we need to create a design of experiments in which we have to insert a lot of factors (5++) with more than two levels. We are beginners in this field and we would like to know what is the best software to use for this goal between JMPpro and Minitab.
Firstly, I would seriously consider the benefits of incorporating Design of Experiments (DoE) when dealing with more than 5 factors and more than 2 levels. A standard two-level full factorial design for 5 factors requires 32 runs. Considering 3 replicates, you would need to conduct 96 individual experiments. However, this approach only provides information about main effects and interactions. On the other hand, a Box-Behnken design for 5 factors requires over 40 runs (3 levels by definition), but the power to detect two-factor interactions is very low, below 50%, resulting in no meaningful information about 2FIs. My point is to reconsider the number of factors and levels. In many cases, 3 levels are sufficient to capture a quadratic function. It is important to remember that the goal of DoE is to minimize effort and expenses while maximizing the data obtained.
Regarding software, I am not familiar with Minitab, but JMP Pro is often mentioned in discussions about Design of Experiments so of the two I would choose JMP Pro. Personally, I would recommend using DesignExpert from StatEase.
- Badges
- Science topic
- Similar topics
- Heat