SENSITIVITY (STABILITY) ANALYSIS OF MULTIPLE VARIETY TRIALS, WITH SPECIAL REFERENCE TO DATA EXPRESSED AS PROPORTIONS OR PERCENTAGES

The literature on 'stability analysis', which is better called 'sensit ivity analysis', leaves much to be desired. This paper attempts to cla rify the issues, particularly the effect of the non-linearity of the s tandard model relating variety yields to mean yields over sites. The m odel is extended from its original applications in the analysis of cro p yields to the analysis of measurements that cannot be considered Nor mally distributed, such as disease assessments expressed as percentage s or proportions. Modern computer software offers a method that is the oretically sound and can be applied routinely to data of many differen t distributional types. Graphical methods of displaying the results of the analysis of non-Normal data are discussed.