Advances in Longitudinal Survey Methodology

5The Effects of Biological Data Collection in Longitudinal Surveys on Subsequent Wave Cooperation

Fiona Pashazadeh¹, Alexandru Cernat¹, and Joseph W. Sakshaug^{2, 3, 4}

¹Department of Social Statistics, University of Manchester, Manchester, UK

²Statistical Methods Research Department, Institute for Employment Research, Nürnberg, Germany

³Department of Statistics, Ludwig Maximilian University of Munich, Munich, Germany

⁴School of Social Studies, University of Mannheim, Mannheim, Germany

5.1 Introduction

There are many considerations in the design and implementation of large‐scale, nationally representative longitudinal surveys in order for researchers to maximise data quality while ensuring cost effectiveness (Buck et al. 1995; Lynn 2009a). Increasing the range of data available by adding new components to an established longitudinal survey, such as linkage to external administrative data, biological data collection or time‐use diaries, can be hugely advantageous for research while also making use of existing data collection structures. However, the additional respondent burden involved may increase the likelihood of non‐response and attrition, compromising the power and representativeness of the sample. Consequently, results of any analysis using the data may be biased, especially when the lack of cooperation is linked to the outcome(s) of interest (Groves 2006). This is of particular concern in longitudinal surveys where the effects of non‐response can be cumulative (Watson and ...