Partial aliased effect number pattern and selection of optimal compromise designs (Q2312011)

This paper is a contribution to the very popular field of fractional factorial design. If the focus is on good estimation of a predescribed number of main effects and two-factor interactions, the design is called compromise design. The authors introduce the so-called partial aliased effect number pattern (P-AENP) and use it for comparison of designs. So they study two-level compromise designs and find theoretical results on so-called clear compromise designs (CCD), strongly clear compromise designs (SCCD) and general optimal compromise designs (GOCD). A number of CCD's, SCCD's and GOCD's with 8, 16, 32 and 64 runs are tabulated.