The potential use of artificially produced monozygotic twins for comparative experiments.

The uniformity of twins has been examined by assembling estimates of the intraclass correlation coefficient (rho(I)) available in the literature for a variety of parameters studied in cattle monozygotic twins and human dizygotic and monozygotic twins. The values of rho(I) vary considerably between parameters. In human monozygotic twins rho(I) is always larger compared to that found in dizygotic twins. There is insufficient evidence to determine whether artificial monozygotic twins are more uniform than natural monozygotic twins. A new measure of twin uniformity, given by T (3) = 1 (1-rho (I)) , is introduced. In practice 2T(3) gives the number of animals chosen at random that one member of a twin pair can replace without loss of statistical efficiency. A useful class of experimental designs for the exploitation of twin uniformity is incomplete block designs. These designs are defined by (v, k, b), where v is the number of treatments to be compared, k = 2, and b is the number of twin pairs. Each design has an associated efficiency (E). Provided rho(I)>1-E, an incomplete block design will be advantageous. In general, when only a few twin pairs are available, this relation will only hold for monozygotic and not dizygotic twins. Suitable arrangements of treatment comparisons for designs (3,2,8), (4,2,9), (5,2,10), (6,2,11) are presented.