Description

Data management: The building blocks of clean, accurate and reliable longitudinal datasets

ANNA GRAVES

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

JEAN BALL

Prostate Cancer Clinical Trials Group, The University of Newcastle, Callaghan, NSW, Australia

ELIZA FRASER

School of Population Health, The University of Queensland, Herston QLD, Australia

ABSTRACT

Data management involves the planning, management and production of data in a format suitable for researchers to use. The products of longitudinal studies are the datasets. Efficient and careful data management will result in datasets that are as accurate and as complete as possible. In addition, effective data management can reduce missing data and minimise data entry error. The final dataset must be in a form that is easy to understand and to use with a variety of statistical packages. Most importantly, data management processes and manipulations must be reproducible and well documented. This paper aims to provide some insight into data management procedures, using the Australian Longitudinal Study on Women’s Health (ALSWH) as an example.

Keywords: longitudinal studies; data management; dataset; recoding; derived variables