Design of Experiments with Two- and Four-Level Factors

Practitioners familiar with the design of two-level fractional factorials are often frustrated when confronted with factors that have more than two levels. This article provides a guide for the inclusion of four-level factors into standard two-level factorial designs. Tables are presented to allow for the design of experiments with two-level and four-level factors using the same types of experimental design criteria commonly used for designing two-level fractional factorials. The concepts of resolution, aberration, and foldover are explained in the context of experiments with two-level and four-level factors. Several new minimum aberration designs that are not in the literature are listed in the tables, and new follow-up designs for the recommended experiments are also provided.