A strategy of experimentation for researchers

A successful research strategy lays out a path with small steps that allows for changes in direction along the way. The “SCO” flowchart for experimenters (Figure 1) is a prime example of such a template for success. Its tried-and-true core is screening (“S”), characterization (“C”) and optimization (“O”). One last, but perhaps most important, step is added: Confirmation. Let’s dive into the SCO strategy for researchers and find out what makes it work so well. The starting point is the Screening design. Screening designs provide a broad, but shallow, search for previously unknown process factors. Use a two-level factorial design to quickly identify variables that affect the responses. TIP – to keep the number of runs lower, don’t bother screening factors that are already known to affect your responses! Newly discovered factors—the “vital few” will carry forward into the next phase of experimentation, with the “trivial many” being set aside. By using medium-resolution (Res IV) designs, you can estimate the main effects cleanly—their effects unbiased by hidden interactions. Moving ahead to Characterization with the vital-few screened factors plus the big one(s) you originally set aside, the identification of two-factor interactions becomes the goal. This necessitates a high-resolution design (Res V or better). Be sure to add center points at this stage so you can check for curvature (non-linearity). If curvature is NOT significant, then your mission is nearly complete—all that remains is Confirmation! If curvature does emerge as being significant and important, then move on to Optimization using response surface methods (RSM). The beauty of RSM is that you can use contour and 3D surface maps to see where each response peaks. Also, via numerical optimization tools, you can pinpoint the setup of factors producing the most desirable outcome for multiple responses. Graphical optimization via overlay plots lays out a compelling visual of the sweet spot—the window where all specifications can be achieved. Last, but not least, comes Confirmation. Decide if you want to confirm one specific “optimal” location in the design space, or if your interest is in verifying a broader area.