Description

Working with longitudinal data: Attrition and retention, data quality, measures of change and other analytical issues

ANNE YOUNG, JENNIFER POWERS AND VIRGINIA WHEWAY

Research Centre for Gender, Health and Ageing, University of Newcastle, Callaghan, NSW, Australia

ABSTRACT

Longitudinal studies are important because they can help provide answers to questions about cause and effect, although their complexity leads to a number of challenges for the researcher. By their very nature longitudinal studies may continue over a long period of time and/or have many data points and therefore good documentation of procedures is essential. In addition, it is important to develop dynamic databases that reflect the current status of participants in the project and to develop protocols for dealing with inconsistent or missing responses over time. This paper provides some guidance about these issues as well as information about longitudinal data structure and ways to summarise and display the information obtained from longitudinal studies.

Keywords: longitudinal studies; panel studies; research methods