Selection of Defining Contrasts and Confounded Effects in Two-Level Experiments

SUMMARY In factorial experiments the selection of defining contrasts and effects to be confounded with blocks is not always straightforward and plans presented in standard texts are not necessarily suitable. A systematic procedure for selecting suitable defining contrasts has been presented by Greenfield (1976). In this paper we show that Greenfield's algorithm does not always generate the smallest possible fraction, and give a more general procedure which is suitable for selecting defining contrasts and confounded effects.