 |
Longitudinal studies |
What are longitudinal data sources?
Longitudinal studies are data sources that contain observations of the same
research units over a period of time. Such data can be collected either through
surveys, or through linkage of administrative data. The
ONS Longitudinal Study of England and Wales,
Scottish Longitudinal Study
and
Northern Ireland Longitudinal Study
are examples of the second kind. They consist of linked census, vital event
and registration data (such as births, deaths, cancer registrations and hospital
discharges).
What can they tell us?
Longitudinal studies are useful for studying individual-level change over time,
in contrast to cross-sectional datasets (such as the census itself), which provide
a snapshot of a population at a single point in time (or at repeated intervals, as
in a time series). Time, however, is itself one of the most important explanations
of change. Therefore, longitudinal studies can give answers to questions concerning
change that cross-sectional studies cannot.
The ONS Longitudinal Study has been used to answer such questions as: how has
the profile of Britain's ethnic populations changed; is there an increase in
co-residence between adult children and their elderly parents in England and Wales,
and does health-selective mobility account for socio-economic differences in health?
Census-based longitudinal studies in the UK
Since 2006 the UK has been covered by three census-based longitudinal studies covering
approximately 1.3 million people (500,000 in England and Wales; 500,000 in Northern Ireland and 300,000 in Scotland).
The
ONS Longitudinal Study of England and Wales (initially known as the OPCS Longitudinal Study) is the longest
established of these, having been set up in the early 1970s. It contains linked census and vital event data for
one per cent of the population of England and Wales. Information from the 1971, 1981, 1991 and 2001 Censuses has been
linked across censuses as well as information on events such as births, deaths and cancer registrations.
The
Scottish Longitudinal Study contains linked census and vital event data for 5.3 per cent of the population
of Scotland. Information from the 1991 and 2001 Censuses has been linked as well as information on events such as
births, deaths, marriages, migrations in or out of Scotland, cancer registrations and hospital discharges.
The
Northern Ireland Longitudinal Study holds linked information from census, vital events and
health registration datasets. Data sources include 2001 Census data, birth and death registrations
and demographic data derived from health registrations.
These census-based longitudinal studies are complex large scale datasets which may be analysed
using a range of statistical methods. Because they include individual-level census data, they are
subject to stringent confidentiality rules.
Access to the data of the census longitudinal studies
To obtain access to Longitudinal microdata there is a process of direct application for UK academics
to the
Centre for Longitudinal Study Information and User Support
(CELSIUS) for England and Wales, the
Longitudinal Studies Centre - Scotland
(LSCS) for Scotland and the
Northern Ireland Longitudinal Study Research Support Unit
(NILS-RSU) for Northern Ireland.
In the case of the England and Wales LS, non-academic users and academic users from outside the UK should approach the
LS Unit at ONS
directly.
Other longitudinal studies in the UK
The UK also has a number of longitudinal studies based on surveys, such as the
British Household Panel Survey, consisting of a nationally representative sample of about
5,500 households recruited in 1991, containing a total of approximately 10,000 interviewed individuals,
and the
English Longitudinal Study of Ageing, the first
study in the UK to connect the full range of topics necessary to understand the economic, social,
psychological and health elements of the ageing process.
The
Centre for Longitudinal Studies houses three internationally-renowned birth cohort studies: the
1958 National Child Development Study, the 1970 British Cohort Study and the Millennium Cohort Study.
The
ESRC United Kingdom Longitudinal Studies Centre is a national resource centre for promoting
longitudinal research and for the design, management and support of longitudinal surveys.
A fuller list of UK longitudinal studies can be found at:
Links to UK Longitudinal Surveys
Further reading
Introductions to the census-based longitudinal studies are available on the Census.ac.uk web site:
The web sites of the longitudinal studies provide a wealth of both general and detailed information, including publications based on longitudinal data. However, the following are more general resources which may be of relevance to anyone wishing to know more about longitudinal studies, how they can be analysed, and within which theoretical frameworks they fit.
Blackwell L. et al, (2005) Opportunities for new research using the post-2001 ONS Longitudinal Study, Population Trends, 121: 8-16.
Brassett-Grundy, A. (2003) Researching Households and Families using the ONS Longitudinal Study. London: Office for National Statistics.
Blossfeld, H.P. and Rohwer, G. (2002) Techniques of event history modelling: new approaches to causal analysis, 2nd ed. Mahwah, NJ: Erlbaum.
Diggle, P.J. et al (2002) Analysis of longitudinal data, 2nd ed. New York: Oxford University Press.
Duncan, T.E. et al (1999) An introduction to latent variable growth curve modeling: concepts, issues, and applications. Mahwah NJ: Erlbaum.
Giele, J.Z. and Elder, G.H. (Eds) (1998) Methods of life course research: qualitative and quantitative qpproaches. Thousand Oaks, CA: Sage.
Hattersley, L., and Creeser, R. (1995) The longitudinal study, 1971-1991: history, organisation and quality of data. London: Office of Population Censuses and Surveys.
Singer, J.D. and Willett, J.B. (2003) Applied longitudinal data analysis: modeling change and event occurrence. New York: Oxford University Press.