DESIGN OF EXPERIMENTS FOR MULTISTAGE PROCESSES

Many industrial processes involve large numbers of input variables so that a complete factorial design would require prohibitively many expe rimental runs. This is particularly the case with multi-stage processe s. We offer a view of multi-stage processes, in terms of autoregressiv e models, which can help in the sensible reduction in the size of expe riments and can also allow different stages of the process to be inves tigated separately.