ANALYSIS OF UNBALANCED SERIES OF VARIETY EXPERIMENTS

Abstract

It is very common in variety improvement programs for many crops, as in the case of sugar cane, that unbalanced series of experiments are projected through space and time, where the imbalance appears, fundamentally, due to the unequal numbers of repetitions of the treatments; in this case the varieties. There is, however, in the usual situations, a "connection" between varieties in such a way that the estimation of any contrast between variety effects is possible; Such connection between varieties is provided by controls that are usually the same for all experiments. And so, even if there are extreme cases of varieties that only appear in an experiment, if there is a connection, it is possible to compare them with the rest of the varieties.