Multi-type step-wise group screening designs with unequal a-priori probabilities

Abstract

In this paper, we discuss multi-type step-wise group screening in which group-factors contain differing number of factors. We describe a procedure for grouping the factors in the absence of concrete prior information, so that the relative testing cost is minimal. We shall derive an expression for the expected number of runs in an Hype step-wise group screening design with unequal group sizes and obtain values of the group sizes that minimize the expected number of runs.