Administrative vs survey data for longitudinal analyses

Abstract

Executive summary

Social longitudinal analyses in the UK have largely been based on survey data, assisted by the investment on cohort and panel studies. In recent years there has been a move to utilise alternative data sources and particularly administrative data. The differences in properties in and benefits and drawbacks of the different types of data are summarised.

Administrative data sources are becoming more widely used in a range of contexts, but it is more challenging to discover the detailed changes and metadata. It is recommended that the possibility of commissioning ‘administrative data biographies’ should be explored, which will describe the evolution of the administrative sources and the way the information in them is gathered.

Linked administrative data and combined administrative and survey data present a wider range of analytical possibilities, but there are challenges in consent for linkage and in undertaking the linkage itself.

A spine is a list of people derived from one or more administrative sources, and to which other data can be linked. We describe some of the considerations in constructing and using a spine in support of longitudinal survey taking.

More information

Identifiers

ORCID for Paul A. Smith: orcid.org/0000-0001-5337-2746

ORCID for Ann Berrington: orcid.org/0000-0002-1683-6668

ORCID for Peter W.F. Smith: orcid.org/0000-0003-4423-5410

Catalogue record

Export record