Sample Size

A recommended number of data runs for a "medium variance" experiment is about 10 per factor. Often that ratio is limited by schedule or cost only to main factors, without interaction factors. A screening experiment often uses only 1-2 runs per main factor. A compromise is to use 2-3 runs for each starting factor and interaction, with the expectation that some factors and interactions will be found to be "not significant". When the selected design does not appear to have an adequate ratio the design may be replicated. The Minimum Detectable Effect can be estimated for a design array or a final design array with replicated and repeated runs. The expectation that some factors will be less important than others is referred to as the Pareto principle.

Learn more about the DOE tools for designed experiments in Six Sigma Demystified (2011, McGraw-Hill) by Paul Keller, in his online Intro. to DOE short course (only $99) or online Advanced Topics in DOE short course (only $139), or his online Black Belt certification training course ($875).