ABSTRACT
In longitudinal analysis, individuals are followed in time and are observed either continuously or at points in time. These contributions are enhanced when microsimulation is viewed as a form of sampling of a virtual population, an approach advocated by e.g. and adopted in this chapter. In discrete-time microsimulation the duration between events can be determined only approximately, whereas it can be determined precisely in continuous-time microsimulation. This chapter discusses two distributions: the Gompertz distribution and the Cox model. It considers multiple origins and multiple destinations and introduces covariates and applies a transition model and continuous-time microsimulation to assess the effects of an intervention programme on the life histories of members of the virtual population. The main tool for continuous-time microsimulation is the inverse distribution function or quantile function.
