Experiments with business processes?

The design of experiments(DoE) process is a systematic series of tests used to determine relationships of x and y variables that affect a process and response.  The results of the experiment are analyzed to find the regression equation that relates the factors to the response.  The Taguchi Method (Design of Experiments) and other methodologies have made major contributions in the reduction of variation and greatly improved engineering quality and productivity by reducing environmental variation. Design of experiments deals with planning, conducting, analyzing, and interpreting controlled tests to evaluate the factors that control the value of a parameter.

Design principles:

• Order is the numeric progression in which a product or service is produced.

• Efficiency is the lowest possible variance from any estimator divided by the expected variance of the selected estimator.

• Randomization is used in experimental designs to prevent systematic patterns and to convert patterns into variation that can be detected in analysis.

• Blocking is a technique used to manage nuisance factors that may affect the results of an experiment. The experiment is organized into blocks and the nuisance factor is maintained at a constant level in each block.

• Interaction is the combined effect of inputs instead of the sum of the individual effects.

• Confounding is used in experimental design. Factors are confounded when the design array is configured so that the effect of one factor is combined with the other.

• Resolution is the criteria used to select a fractional factorial design.

The goal of the Design of Experiments is to discover the relationship between the factors that affect a process and the response.  In the experiment, the factors are varied systematically, and then the resulting response observed. The results of the experiment are analyzed to find the regression equation for the response.  DoE is covered at the Six Sigma Black Belt level of training.