Definition

An experimental design that allows one to evaluate the effects of a large number of potential Factors on the response in the fewest possible runs, in order to screen out the trivial many and identify the significant few that drive the response. These designs tend to be highly fractionated, with the attendant problems of aliasing and low resolution. However, if only a few of the Factors are expected to have large effects, this design can identify them in a cost-effective manner.

The other advantage of screening designs is that they can be used as a first iteration in the analysis, and can be augmented with additional runs in order to break certain key aliases if the need arises. Also, once the key Factors have been identified, focus shifts to only those Factors and the effect of the 'hidden replication' or projection property of the design can be used to advantage in this case.

External Links

Screening Designs from NIST: - http://www.itl.nist.gov/div898/handbook/pri/section3/pri3346.htm