The stability of yield is an important characteristic to be considered when judging the value of a cropping system relative to others. In the context of agricultural research, the analysis of yield stability has been largely confined to multienvironment trials of crop cultivars. This review emphasizes that methods for comparing the stability of cultivars can also be used for comparing different agronomic treatments in general, of which cultivars are but a special case. Throughout the paper, different agronomic treatments are referred to as cropping systems. Some of the methods useful for stability analysis of cropping systems are discussed and a brief review of applications of these methods is given. The paper puts different stability measures into a unifying mixed model perspective.

Multienvironment trials are often analyzed to assess the yield stability of genotypes. Most of the common stability measures correspond to parameters of a mixed model with fixed genotypes and random environments. Analysis within a mixed model framework allows unbalanced data to be handled. This note shows how to fit the most common stability models using the MIXED procedure of the SAS system.

Summary. Multitiered experiments are characterized by involving multiple randomizations, in a sense that we make explicit. We compare and contrast six types of multiple randomizations, using a wide range of examples, and discuss their use in designing experiments. We outline a system of describing the randomizations in terms of sets of objects, their associated tiers and the factor nesting, using randomization diagrams, which give a convenient and readily assimilated summary of an experiment's randomization. We also indicate how to formulate a randomization-based mixed model for the analysis of data from such experiments.

We propose the application of Enviromics to breeding practice, by which the similarity among sites assessed on an "omics" scale of environmental attributes drives the prediction of unobserved genotypes.

Many experiments involve a complex treatment structure, and it is not always immediately obvious how such experiments should be analysed. This paper shows by way of three examples how a suitable linear model can be formulated that provides a meaningful analysis of variance table and allows mean comparisons of interest to be obtained in a straightforward manner. Possible advantages of this approach compared to the use of linear contrasts are discussed. It is concluded that a well-chosen model can often considerably simplify the analysis and lead to useful statistical inferences. The approach advocated in this paper is going to be strongest when there is good design structure present.