Results on constructing [formula omitted] regular designs with general minimum lower-order confounding

Abstract

For s-level regular designs, an aliased component effect-number pattern (AENP) can be used to investigate all of confounding information among factorial component effects. Based on the AENP, we introduce general minimum lower-order confounding (GMC) criterion to choose optimal sn−m designs, where s is a prime or prime power. We first have an overview of GMC theory and introduce s-level GMC criterion. Then, some properties are provided to study s-level GMC designs in terms of their complementary sets. Further, we obtain the lower-order confounding expressions of the constructed GMC designs. Some examples are given to illustrate these results.