All statistics for Create Taguchi Design

Find definitions and interpretation guidance for every statistic that is provided when you create a Taguchi design.

In This Topic

Taguchi orthogonal array
Factors
Runs
Signal

Taguchi orthogonal array

Taguchi orthogonal arrays are experimental designs that usually require only a fraction of the full-factorial combinations. Many orthogonal arrays are available in other forms, such as fractional factorial and Plackett-Burman designs. The arrays are designed to handle as many factors as possible in a certain number of runs. Create Taguchi designs by assigning some or all the array columns to the factors in your experiment. For more information, go to Catalogue of Taguchi designs.

Interpretation

The columns of the arrays are balanced and orthogonal. This means that in each pair of columns, all factor combinations occur the same number of times. Orthogonal designs let you estimate the effect of each factor on the response independently of all other factors.

The notation L(runs) (levels ^ factors) indicates the following:

L(runs) = number of runs
(levels ^ factors) = number of levels for each factor ^ number of factors

For example, an L8 design has 8 runs. (2^3) or (2 ³) means 3 factors at 2 levels.

If your notation is L(runs) (number ^ exponent number ^ exponent) then you have a mixed-level design. For example, an L18 (2^1 3^7) means that the design has 18 runs, 1 factor with 2 levels, and 7 factors with 3 levels.

Factors

The number of control factors in the design.

Interpretation

The factors are the variables that you control in the experiment. Factors are also known as independent variables, explanatory variables, and predictor variables. Factors assume only a limited number of possible values, known as factor levels. Factors can have text or numeric levels. For numeric factors, you select specific levels for the experiment, even though many values for the factor are possible.

The goal of the experiment is to select the control factor levels that minimize the effect of noise factors on the response. Examples of control factors are equipment settings, the type of materials used to manufacture the product, or product design features. For more information, go to Factors in Taguchi designs.

Runs

The number of rows of data in the design.

Interpretation

A run is an experimental condition or factor level combination at which the response is measured. The number of runs is the number of rows in the basic Taguchi orthogonal array. It indicates the number of distinct control factor combinations to be run in the experiment.

Suppose you have a design with 3 control factors with 2 levels each. Your experiment has 4 runs:

C1	C2	C3
A	B	C
1	1	1
1	2	2
2	1	2
2	2	1

For the second run (second row), you would set Factor A low, Factor B high, and Factor C high.

For each control factor level combination, there are multiple experimental runs at the various noise factor conditions. For each noise level condition, there is a separate response column in the worksheet.

C1	C2	C3	C4	C5
A	B	C	Noise level 1	Noise level 2
1	1	1
1	2	2
2	1	2
2	2	1

For the second run (second row), you would set Factor A low, Factor B high, and Factor C high, and record the responses for each level of the noise factor.

Signal

Indicates the name of the signal factor.

Interpretation

A signal factor is a factor with a range of settings that are controlled by the user when using the product. Signal factors are used in dynamic experiments, in which the response is measured at each level of the signal. The goal of the experiment is to improve the relationship between the signal factor and the response.

An example of a signal factor is gas pedal position. The response, the car's speed, should have a consistent relationship with the amount of pressure applied to gas pedal. For more information, go to Factors in Taguchi designs.