Data considerations for Define Custom Split-Plot Design

Consider the following guidelines when you define the design.

The design should be to study 2-level factors
Text factors must have exactly two levels. To allow for botched runs, numeric factors can contain any number of values.
The size of the design should be adequate
The sample size and power should be desirable for a practically important effect size. To evaluate the statistical significance of whole plots, the design requires one whole plot for each level combination of your hard-to-change factors.
The design should have 1 to 3 hard-to-change factors
A hard-to-change factor is a factor that is difficult to randomize completely because of time or cost constraints. For example, temperature is a common hard-to-change factor because temperature often requires significant time to stabilize after a modification.
The run order should be randomized for data collection
If the worksheet contains a column that contains the run order, you can specify that column when you define the design. Otherwise, you can randomize the design after you define the design with Stat > DOE > Modify Design.
A column should exist that identifies whole plots or the runs in the same whole plots should be in contiguous rows
If the worksheet contains a column that identifies which runs are in each whole plot, you can specify that column when you define the design. Each whole plot should have a different symbol, even if it contains experimental runs that are a replicate of another whole plot. Alternatively, you can specify the whole plot size and Minitab creates a column for you. The numbers in the new column are repeated the same number of times as the size that you specify. Thus, the whole plot rows should be together in the worksheet.
By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy