[A methodological review of specific techniques of time series analysis in epidemiology and public health].

Time series analysis of health indicator can contribute to the improvement of knowledge in epidemiology and public health. It is necessary to use models and methods appropriate to the time domain. A class of models proposed by Box & Jenkins are presented together with the necessary tools for identifying such models. Two useful generalisations are also discussed. To study the link between two time series, regression models need to include autocorrelated error terms while to evaluate the effect of an intervention, the use of intervention models are appropriate. This paper presents basic concepts of such analyses in a simple way to encourage the use of those methods.