A comparison of several design augmentation strategies

Industrial experiments often involve many variables, of which only a few ar e expected to be important. Typically a sequential design approach is used in which a screening phase is followed by a more detailed design on a subse t of the variables. Screening designs are usually highly-fractionated facto rials or Plackett-Burman designs; the subsequent stages usually involve fol ding over the Plackett-Burman design, augmenting the fractional factorials, or a completely new less-fractionated factorial using a subset of the orig inal variables. In all of these designs, the alias structure can cause diff iculties in detecting the correct model. This paper examines the foldover p roperties of the Plackett-Burman versus those of three-quarter fractional f actorials, comparing and contrasting the efficacy of these two alternative approaches relative to convergence to an a priori known correct model. The results suggest that an initial fractional factorial (that can be subsequen tly extended to a three-quarter fraction) supports better model identificat ion than the Plackett-Burmann design (with subsequent full foldover). Copyr ight (C) 2000 John Wiley & Sons, Ltd.