Management of Parametric Response in Design of Experiments

Routine applications of design of experiments (DOE) by non‐mathematicians assume that each response value is static in nature, i.e. with an expected value that is constant for a given set of input factor settings. When this assumption is not valid, it is important to capture the dynamic characteristics of the response for effective process or system characterization, monitoring, and control. With the purpose of recognizing the self‐changing nature of the response owing to factors other than those built into the DOE, thereby gaining a better ability to shape the behavior of the response, this paper describes the reasoning and procedure needed for such ‘parametric responses’, via common techniques of mathematical modeling and optimization. The procedure is intuitive but essential and useful in DOE studies as these become increasingly popular by practitioners in the context of improvement projects such as those related to Six Sigma or stand‐alone performance optimization initiatives.