Split-plot experimental designs for combinatorial and high-throughput experimentation

In the last few years, high-throughput reactors have small received significant attention due to the potential they offer for fast material development. While many experimental design techniques are proposed, statistical issues related to experimentation in this type of equipment are emerging. One of the experimental design techniques needed is the split-plot approach, given the randomization restrictions imposed by the equipment. This paper presents the use of split-plot experimental designs in a high-throughput reactor. We discuss the unique error structure of these designs and the special statistical analysis that considers two different types of errors. A case study in the Dow Chemical Company is presented. The main advantage of the split-plot approach related to high throughput is that reactor-well utilization can be maximized, while randomization restrictions can be addressed correctly and simultaneously. The results obtained indicate the success of this strategy in maximizing the chance of detecting a lead and making the right conclusions, which is of key importance given the speed of data generation of high-throughput reactors.