Explores how controllable variables can be used to mitigate the effects from the uncontrolled variables.

This DOE array is particularly popular in the field of robust design. A fundamental concept of this methodology is the classification of variables into two distinct groups: independent controlled variables and uncontrolled variables (sometimes called noise).

Consider the simple example of how the selection of a particular alloy for manufacturing could reduce the frequency of manufacturing outliers due to thermal effects (for example, a particular alloy is less sensitive instead of noise).

Usability Characteristics

  • Taguchi arrays have a resolution type III. However, unless there is intent to use Taguchi arrays specifically, in most cases it is recommended that you use the Fractional Factorial DOE with resolution III, which can result in Taguchi arrays in some conditions.
  • The effects between the controlled variables are confounded with respect to their two-factor interactions so the controlled variables should be selected to have no interactions between themselves. In this condition the calculation of the controlled variables are valid.
  • The interaction between the controlled and uncontrolled variables are valid and often are the main result of interest.
  • Any data in the inclusion matrix is combined with the run data for post-processing. Any run matrix point which is already part of the inclusion data will not be rerun.


In the Specifications step, Settings tab, change method settings.
Parameter Default Range Description
Design Auto Select
  • Auto Select
  • L4
  • L8
  • L9
  • L12
  • L16a
  • L16b
  • L18
  • L25
  • L27
  • L32a
  • L32b
  • L36a
  • L36b
  • L50
  • L54
  • L64a
  • L64b
  • L81
Choose the array for the variable set.
Resolution III III Select the resolution.
Number of Runs 1.1 ( N + 1 ) ( N + 2 ) 2 > 0 integer Number of new designs to be evaluated.
Use Inclusion Matrix Off Off or On Concatenation without duplication between the inclusion and the generated run matrix.