Summary
Studies that collect longitudinal data are especially important for demographers. Longitudinal data are those derived from repeated measurements on individuals who have been studied for a period of time. They permit the calculation of the number of events per unit time, i.e. a rate. The events of interest can be anything, for example: births, deaths, marriages, incidence of disease. Demographic studies that generate longitudinal data are typically community or population-based.
Collecting data on the events as they occur (prospective data collection) increases the accuracy of the data collected by minimising recall bias. It also ensures that the study can potentially reach all the members of the target population at the time the event occurs. Prospective studies generate longitudinal data in which factors of interest are ascertained before the outcome of interest. This makes it possible to investigate causal hypotheses. A potentially causal factor can be measured at a time pre-dating the outcome under study which cannot be done in other, retrospective study designs. This is a great strength of these studies but following up participants over time is resource intensive and logistically demanding. These studies can generate a large volume of complex data that requires special skills to analyse correctly.
Health and Demographic Surveillance Systems are continuous studies which exist to provide demographic information in settings where there is no system for vital registration. They collect data on demographic events at regular intervals from a defined population and can be used to track trends over time and to understand variations in rates within a population. Many also include measurement of specific markers of health and disease.