ABSTRACT
Individual changes in growth, development and health can only be studied if the same individuals are measured repeatedly over a period of time. This is called a longitudinal study. However, longitudinal designs also have their constraints: No matter which design has been used, always confounding effects will occur. Three classical research designs can be discerned: (1) a cross-sectional design, (2) a time-lag design and (3) a longitudinal design (see Figure 48.1). Graphical representation of the three classical research designs: vertical bar, cross-sectional design; diagonal bar, time lag design; and horizontal bar, longitudinal design https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9780203852026/3a9e878d-0653-4830-8f7f-e05afe24449a/content/fig48_1_B.tif" xmlns:xlink="https://www.w3.org/1999/xlink"/> Each measurement taken on a subject at a particular point of time is influenced by three factors: (1) The chronological age of the subject, defined as the period that elapses between the date of birth and the time of measurement. The age effects produce the mean growth curve. (2) The birth cohort to which the subject belongs. This is defined as the group of individuals born in the same year. Cohort effects can be used to study secular trends. (3) The time of measurement is the moment at which the measurement in the subject is taken. Time of measurement effects are related to changes in environmental conditions that can occur over a period of time.
