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.