Select DOE > Screening Design from the main menu. In the Responses panel, there is a single default response called Y. Do the following in the Factors panel:
1.
|
2.
|
Select 6 Level from the Categorical list. This adds the variable X2, with levels L1, L2, L3, L4, L5, and L6.
|
3.
|
Enter 11 in the box to the right of Add N Factors.
|
4.
|
Click Continuous. This adds 11 factors, X3 to X13, each at two levels, -1 and 1.
|
When you click Continue, the Design Generation panel appears (Screening Design Dialog for 13 Factors, with Design Generation Panel). Note that the option of selecting a design from the Design List does not appear, as there is no available standard design for this experimental situation.
The Back button gives you the option to return to the Responses and Factors panels. Accept the default number of runs (24) and click Make Design.
The randomized design is shown as part of the Screening Design report. The algorithm that generates the design is stochastic, so to reproduce this design, you need to save the script with the random seed. (To do this, select Save Script to Script Window from the red triangle menu next to the report title.)
To see that this specific design is orthogonal, click the disclosure icon next to Design Evaluation. Next, click the disclosure icon next to Color Map On Correlations. The color map (Color Map on Correlations) shows red entries corresponding to correlation of one on the main diagonal. Off-diagonal correlations are all deep blue, indicating that correlations between the parameters are all zero.