Covering Array Options
The red triangle menu in the Covering Array platform contains these options:
Save Factors
Creates a data table containing a column for each factor that contains its factor levels. Each factor’s column contains these column properties: Design Role, Value Order, and Factor Changes. Saving factors enables you to quickly load them into a DOE window.
Note: You can create a factors table for a Covering Array by entering data into an empty table, but remember to assign each column an appropriate Design Role of Categorical. Right-click the column name in the data grid and select Column Properties > Design Role. In the Design Role area, select Categorical.
Load Factors
Loads factors that you have saved using the Save Factors option into the Factors section.
Load Design
Loads a design from the active data table. If no data table is active, you are prompted to open one. When you select Load Design, a menu appears that enables you to select the columns that you want to specify as factors in the design. All columns are imported as categorical. Columns and their values are listed in the Factors section. The Design section shows a Run for each row in the data table and gives the values of the factors for each run.
The Load Design options enables you to obtain metrics, modify, or construct an Analysis script for an existing design:
– The Metrics section shows t-Coverage and t-Diversity for the specified design.
– You can click Back to impose factor level restrictions and then construct a new design.
– Clicking Make Table constructs a design table where you can enter responses. The table contains an Analysis script for the design.
Set Random Seed
Sets the random seed that JMP uses to control certain actions that have a random component. For Covering Arrays, the seed selects a starting design and an iteration count. For most designs, the random seed guarantees reproducibility of the design, but not of the run order.
Note: Upper limits on time as well as iteration count are used to limit design construction time. For some large and high strength designs, depending on the machine, the time limit might override the iteration limit. For such designs, the random seed does not guarantee reproducibility.
To reproduce a design, enter the random seed used to generate it before clicking Make Design.
Note: The random seed associated with a design is included in the DOE Dialog script that is saved to the design data table.
Simulate Responses
Adds simulated response values to the Response column in the design table. Select this option before you click Make Table.
When you click Make Table, the following occur:
– The Response column is populated with simulated values.
– A Simulate Responses window appears where you can specify one of two simulations.
• Specify Failure Count simulates random failures based on the specified Expected Number of Failures.
• Specify Root Cause simulates a failure for each covering array run that matches the specified combinations of root causes. Select the factor level combinations, Add, and then Apply to update the simulated Response values.
– A script called DOE Simulate is saved to the design table. This script reopens the Simulate Model window, enabling you to re-simulate values or to make changes to the specified simulation.
Save Script to Script Window
Creates the script for the design that you specified in the Covering Array window and places it in an open script window.