ABSTRACT
There are several empirical contexts in which a subset of the population might behave differently to those individuals whose behaviour is characterized by the proposed mixed generalized linear model. For instance, in a migration study, we could observe a group of respondents who do not move outside the study region over the study period. These observed non-migrators could comprise two distinct groups. The first group could consist of those individuals that considered migrating, but who were not observed to do so during the study period. The second group could comprise those that would never consider migrating. These non-migrators are known as stayers. In the competing risk context, some individuals may be classified as stayers in the sense that they are not vulnerable to one particular exit condition. For example, few unemployed males are likely to seek part-time work. In biometric research, these ‘stayers’ are often referred to as non-susceptibles.
