EFFICIENT REPEATED MEASUREMENTS DESIGNS WITH EQUAL AND UNEQUAL PERIOD SIZES

We describe a general method of constructing repeated measurements designs using sets of cyclic shifts. Efficient designs for t treatments in p periods, where t less-than-or-equal-to 10 and p periods, where t less-than-or-equal-to 10 and p less-than-or-equal-to 8, are given. In addition, efficient strongly balanced designs and designs that are balanced for first- and second-order residual effects are given. Finally, some efficient designs with two different period sizes are given. The designs extend and fill in gaps in previously published tables.