Search designs for \(2^ m\) factorials derived from balanced arrays of strength \(2(\ell +1)\) and AD-optimal search designs (Q1068499): Difference between revisions

In this paper, the authors consider a search design for the \(2^ m\) type such that at most k non-negative effects can be searched among \((\ell +1)\)-factor interactions and estimated along with the effects up to \(\ell\)-factor interactions, under the assumption that \((\ell +1)\)-factor interactions (other than the k effects) and the higher order interactions are negligible. The properties of a search design based on a balanced \(2^ m\) design of resolution \(2\ell +1\) derived from a balanced array of strength \(2(\ell +1)\) have been investigated and a necessary and sufficient condition for a balanced design of resolution \(2\ell +1\) to be a search design for \(k=1\) is given. Several search designs for \(k=1\), in the class of balanced \(2^ m\) designs of resolution V, which are optimal according to the AD-optimality criterion are presented.