Abstract
A mixture experiment is one in which the response depends only on the proportions of the components present in the mixture and not on the total amount of the components. Experimenters often satisfy this definitional requirement by fixing (holding constant) the total amount of the components. A mixture-amount experiment, on the other hand, is one in which the amount of the mixture varies, and hence the response may depend on the amount of the mixture as well as on the proportions of the components present in the mixture. Piepel and Cornell (1985) have discussed models for mixture-amount experiments. In this article we present and discuss ways to generate complete and fractional designs for both unconstrained and constrained mixture-amount experiments. The designs presented are also applicable to mixture-process variable experiments involving one process variable. Several examples are utilized to illustrate the design development techniques discussed.
Additional information
Notes on contributors
Gregory F. Piepel
Dr. Piepel is a Senior Research Statistician in the Statistics Section. He is a Member of ASQC.
John A. Cornell
Dr. Cornell is a Professor in the Department of Statistics. He is a Senior Member of ASQC.