TABLE OF CONTENTS "I'm very well acquainted, too, with matters mathematical, I understand equations, both the simple and quadratical,"
A VERSE FROM "I AM THE VERY MODEL OF A MODERN MAJOR GENERAL" FROM THE PIRATES OF PENZANCE BY GILBERT AND SULLIVAN
If you've made it this far, you are indeed well acquainted with matters mathematical, particularly those dealing with quadratic equations for response modeling. All of this is easy with numeric (quantitative, continuous) factors, but what if some are categorical (qualitative, discrete), such as type of material or choice of supplier? That's one of the issues we will address in this chapter.
We also discuss the application of RSM to computer simulations, a necessity for modern Major Generals and the suppliers of their high-tech systems. For example, it would be prohibitively expensive to build prototype jet engines for state-of-the-art military aircraft; so instead, the engineers apply computer-based techniques such as finite element analysis to evaluate alternative designs. One compressor may require more than 100,000 elements, which consume days of time on high-cost computers (Myers, Montgomery, 2002, p. 483). Response surface methods quickly and inexpensively ferret out transfer functions (polynomial models) that simplify the search for optimal factor settings.
The developers of response surface methods, Box and Wilson, came out of the chemical industry, as did the authors of this book. Numeric factors abound for this application of RSM, and they are easily adjusted. For example, one of the authors (Mark) began his chemical engineering...
