ASQ

Exclusive Content & Downloads from ASQ

Factorial Experiments When Factor Levels Are Not Necessarily Reset

Summary: [This abstract is based on the authors' abstract.] Industrial experiments are often randomized, but may contain factors that are not reset because of time constraints or cost. This leads to erroneous test results and inferences. Formulas are presented for prediction variance and expected prediction variance that allow comparison of the prediction properties of completely randomized experiments to experiments in which the levels of one or more factors are not reset. Recommendations for carrying out this type of industrial experiment are given.

Please sign-in or register to download this information. Registration is FREE and gives you access to ASQ's articles, case studies and general information.