Statistics for Six Sigma Green Belts with Minitab and JMP

8.4. Fractional Factorial Designs

When you are considering four or more factors (Xs), simultaneously running all possible treatment combinations often becomes costly or impossible. For example, 4 factors each with 2 levels involve 16 treatment combinations; 5 factors each with 2 levels involve 32 treatment combinations; and 7 factors each with 2 levels involve 128 treatment combinations. Thus, as the number of factors in an experiment increases, Six Sigma team members need to have a rational way of choosing a subset of the treatment combinations so that they can conduct a cost-effective experiment with meaningful results. One way to do this is through the use of a fractional factorial design.

In a fractional factorial design, you use only a ...