ESRC award for research on Paradata (field process data)
In recent years, a new class of data, so-called paradata, has been collected by survey agencies. Paradata are a by-product of the data collection process capturing information about that process.
Typical examples are interviewer observations about a sampled household, interviewer call record data, capturing information such as date and time of each call attempt to a household, and key-stroke files, capturing the navigation through the questionnaire. Awareness of the potential benefits of paradata has grown amongst both data producers and data users. However, the use of paradata and its benefits are still largely unexplored.
The key objectives of this research are to investigate the uses of paradata for longitudinal surveys with the aim of improving field process management and intervention decisions during data collection, and to explore how best to use such paradata in statistical models.
The research will be organised into three sub-projects which will: 1) investigate the use of call record data and interviewer observations to study nonresponse in longitudinal surveys, 2) provide insights into the effects of interviewing strategies and other interviewer attributes on response in longitudinal surveys, and 3) gain knowledge about the measurement error properties of paradata, in particular interviewer observations.
Analysis techniques will include multilevel, discrete-time event history and longitudinal data analysis methods. Dissemination will include a short course and an international workshop on paradata.
Related Staff Member
Dr Gabriele B Durrant MSc, PhD
Dr Gabriele B Durrant is Associate Professor within Social Sciences: Social Statistics & Demography at the University of Southampton.
View profile