Sensitivity of Design Optimality Criteria to Second-order Response SurfaceModel Restrictions and Center Point Replications

Abstract

Abstract In this work, we investigate the role of several model characteristics and center point replications on the properties of A-, D-, G-, and IV- optimality for four –factor second-order response surface design. It was discovered that A-, D-, and G- efficiencies tend to reduce as the center points are replicated while the effect on scaled average prediction variance tends to be very insignificant. Among the restricted models considered, the pure linear model (model1) turns out to be the best in terms of quality of estimation and model prediction.

Key words: Design optimality criteria; Center point replications; Response surface methodology