Resolvable block designs for factorial experiments. (Q1298875)

It is known that n-cyclic designs provide a flexible class of designs suitable for setting out factorial experiments. In this paper we show that many of these designs are resolvable. Further, an extensive class of practically useful designs can be derived from them by deleting replicates. The properties of the designs compare favourably with those obtained by the algorithm of \textit{E. R. Williams} and \textit{J. A. John} [J. R. Stat. Soc., Ser. C 45, 39-46 (1996)].