The Canadian Journal of Statistics / La Revue Canadienne de Statistique, Vol. 3, No. 1 (1975), pp. 119-124 (6 pages) Bradley (1958) proposed a very simple procedure for constructing latin square ...
THE efficacy of the Latin-square design 1 in eliminating two-dimensional variation from treatment comparisons, particularly in field experiments, has long been established. Kendall 2 states that ...
One solution of the problem of adding a further set of n non-interacting treatments to an existing n x n Latin square is to use a Graeco-Latin square, if one exists. This solution is never possible ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback