Critical to success is the development of a strategy of experimentation, which streamlines the experimental process. Such
a strategy, summarized in Table 1, identifies three experimental environments: screening, characterization, and optimization.7 The objectives of each of the three phases are summarized in Table 1. The strategy sequences and links together a variety
of experimental designs, which enables scientists to achieve greater results than they could achieve previously using the
same DOE techniques in isolation.
Table 1. Comparison of experimental environments
The strategy used depends on the experimental environment. These characteristics involve program objectives, the nature of
the factors and responses, resources available, quality of the information to be developed, and the theory available to guide
the experiment design and analysis. A careful diagnosis of the experimental environment along these lines can have a major
effect on the success of the experimental program.7
Critical Principles for Experimentation
The screening–characterization–optimization (SCO) strategy is illustrated by the work of Yan and Le-he, who describe a fermentation
optimization study that uses screening followed by an optimization strategy.8 In this investigation, 12 process variables were optimized. The first experiment used a 16-run Plackett-Burman screening
design to study the effects of the 12 variables. The four variables with the largest effects were studied subsequently in
a 16-run optimization experiment. The optimized conditions increased fermentation yield by 54%.
The Screening Phase. The screening phase explores the effects of a large number of variables with the objective of identifying a smaller number
of variables to study further in characterization or optimization experiments. Screening studies typically use fractional–factorial
and Plackett–Burman designs to collect data. More screening experiments involving additional factors may be needed when the
results of the initial screening experiments are not promising. The screening experiment often solves the problem.
The Characterization Phase. The characterization phase helps us better understand the system by estimating interactions as well as linear (main) effects.
The process model is thus expanded to quantify how the variables interact with each other as well as measure the effects of
the variables individually. Full-factorial and fractional–factorial designs are used here.
The Optimization Phase. The optimization phase develops a predictive model for the system that can be used to find useful operating conditions (design
space) using response surface contour plots and mathematical optimization. In these studies, response surface designs are
used to collect data.
The SCO strategy in fact embodies several strategies which are a subset of the overall SCO strategy, including:
The end result of each of these sequences is a completed project. There is no guarantee of success in a given instance, only
that the SCO strategy will "raise your batting average."7