[Spu(2)]Factorial Treatment Structures

This chapter considers the analysis of higher-order treatment structureswhere each of the treatment factors occurs at only two levels. For example a 23 treatment structure experiment would be an experiment involving three treatment factors with each factor at two levels, i.e., a 2 x 2 x 2 experiment. These kinds of experiments are very important for exploratory purposes. They allow researchers to consider experiments which involve large numbers of treatment factors all in one experiment. This is very important because it can be shown that if a researcher wishes to optimize a process (i.e., find that combination of the treatment factors which will give the most desirable outcome), it is almost always more efficient to study all of the factors which are thought to have an influence on the process simultaneously rather than studying each of the factors one-at-a-time by holding all of the other factors fixed. These kinds of factorial experiments are most useful for an initial exploratory study of the process under study. They allow researchers to determine those factors which have the greatest impact on the process under study, and hence experimenters learn which factors should be concentrated on in order to be successful in improving the process. After discovering those factors which have the greatest impact on the process, follow-up experiments can be performed, which should help experimenters fine-tune the process.