The Understanding Society Working Paper Series is a programme of methodological research by the scientific team behind the Study. Here we've brought together Working Papers on linked data.
In this review we discuss how integrated survey and administrative data have been used for research on income and employment, education and health; where the future potential for integrated data lies; how we might think about the quality of integrated data; and what we currently know about different sources of error that can affect integrated data.
We explore the cognitive process by which respondents decide whether or not to consent to having their survey data linked to administrative records. Using data from the Understanding Society household panel study we document the extent of inconsistencies in respondents’ consent decisions, between data domains and over time, and the impact of the mode of data collection on consent.
This research uses a large nationally representative survey asking mothers to consent for both themselves and their children for two sets of records. Nearly all mothers give the same consent outcome for all their children. Consent is higher for education records than for health records and higher for mothers than children. Multivariate analyses suggest that minorities are generally less likely to consent, while more trust increases chances of consent. Several survey environment factors are also important. Findings suggest potential methodologies to improve consent rates, important given significant demographic differences found. However, data from 10-15 year olds in the study shows fewer differences for several important behaviours and attitudes.
Understanding Society was designed to be representative of the UK population using a stratified, clustered, equal probability sampling design. This paper uses Census 2001 data to analyse whether Wave 1 respondents are representative of the different regions of the UK in terms of the types of neighbourhoods individuals live in. Neighbourhoods are classified using Townsend Material Deprivation quintiles and the Census Output Area Classification. We find that the respondent members of the general population sample of Understanding Society closely resemble the Census 2001 population at the neighbourhood level - nationally and regionally.
A range of geographical identifiers are being made available for Understanding Society which allow researchers to merge external data at different geographical levels to individual’s responses. Examples of geographical identifiers at higher level include country and Government Office Region; at medium level Local Authority Districts and Travel to Work Areas; at lower level Lower Layer Super Output Areas. This paper provides a brief introduction to UK geography, gives an overview of the geo-codes available for use with Understanding Society and provides documentation of the variables.