Factor screening and response surface exploration

Standard practice in response surface methodology performs factor screening and response surface exploration sequentially, using different designs. A novel approach is proposed to achieve the two objectives on the same experi ment, based on one design. Running a uni-stage experiment has the advantage s of saving experimentation time and run size. The approach is based on a t wo-stage analysis that employs factor screening, projection and response su rface exploration. Projection-efficiency criteria are defined to evaluate t he performance of the projected designs. The projection-efficiency properti es of the 3(n-k) designs and three nonregular designs are studied, and comp arisons with central composite designs axe made. Nonregular designs appear to enjoy better projection properties. The strategy is illustrated with the analysis of a PVC insulation experiment.