ABSTRACT
The language used in Design of Experiments(DoE) is somewhat different from that used in traditional experiments. Manufacturing companies learn SPC first for two major reasons: the mathematics of statistical process control are easier, and it is necessary to learn about the process and eliminate special causes of variation, that is, to get the processes under control, before the structure of DoE can be applied. There are two major types of DoE: classical and Taguchi. Both types have their proponents and opponents, and sometimes the discussions between the two have been less than uplifting. Classical DoE analyses usually are conducted with more mathematical and statistical rigor than Taguchi analyses. Classical methods emphasize the choice of optimum results by calculation of response surfaces from a single, large experiment. The contribution of uncontrollable factors is of considerable concern in Taguchi experiments. Cost is an ever-present consideration in Taguchi experiments.
