Staggered-level designs for response surface modeling
Faculty of Applied Economics
Antwerp :Universiteit Antwerpen, Faculty of Applied Economics, 2013
Research paper / University of Antwerp, Faculty of Applied Economics ; 2013:027
University of Antwerp
In industrial experiments, there are often restrictions in randomization caused by equipment and resource constraints, as well as budget and time restrictions. Next to the split-plot and the split-split-plot design, the staggered-level design is an in- teresting design option for experiments involving two hard-to-change factors. The staggered-level design allows both hard-to-change factors to be reset at dierent points in time, resulting in a typical staggering pattern of factor level resettings. It has been shown that, for two-level designs, this staggering pattern leads to statis- tical benets in comparison to the split-plot and the split-split-plot design. In this paper, we investigate whether the benets of the staggered-level design carry over to situations where the objective is to optimize a response, and where a second-order response surface model is in place. To this end, we study several examples of D- and I-optimal staggered-level response surface designs.