Frequently asked questions

What is CeLSIUS?

CeLSIUS is the Centre for Longitudinal Study Information and User Support. It is based at the London School of Hygiene & Tropical Medicine and provides support for UK university based users (staff and students) wishing to use the ONS Longitudinal Study (LS). The unit provides advice and information on the design of projects, helps users to complete applications to use the data and produces data extracts, tabulations and analyses specified by users.

Who can use the Longitudinal Study? Do I have to be a member of a university?

Academic researchers, government users and non-governmental organisations may be able to use the LS. CeLSIUS is funded to support UK academic users. It is necessary for an academic user to be a member of staff at a college of further education or a higher education institution or a student at one of these institutions. If you are not a student or member of staff at one of these institutions, you should contact the Office for National Statistics ( about using the LS.

Do I have to pay for CeLSIUS's services or to use the LS?

CeLSIUS is funded by the Economic & Social Research Council (ESRC) and our services are free. There is currently no charge for UK university based academic users for using the data from the LS.

Can I download the data set?

It is not possible to download data sets from the Internet, because of the confidentiality restrictions on the LS. All projects using the LS must be approved by the LS Research Board. There is a short application process for approving projects. Users can decide how they wish to receive their outputs. For more information on the outputs you can receive, see the online training module on LS outputs.

What training is available for using the LS?

CeLSIUS has produced ten interactive online training modules, covering ethnicity, socio-economic indicators, defining a study population, LS outputs, households and families, geography, statistical analyses, fertility, mortality, events.

What documentation is available?

There are a number of different sources of documentation relating to the LS. The CeLSIUS website contains ten online training modules, which provide information on important aspects of the LS data set. A number of publications on the LS are available, which have been produced in different series: LS Volumes, Working Papers and User Guides. The ONS LS website contains information on sampling fractions, linkage rates, tracing rates, census forms, and a link to 2001 Census definitions. Of particular use is Longitudinal Study 1971-1991: History, Organisation and Quality of Data (LS Series No.7), which provides information on the LS up to the 1991 Census. Finally, the Data Dictionary contains information on variables contained in the LS.

What variables does the LS contain?

The LS contains over 2,800 variables, covering individuals in private households and communal establishments, family and household characteristics, information on other household members, geography, occupation, events data (fertility, mortality and cancer registration) and embarkations, immigrations and re-entrants. Variables can be studied using the online data dictionary, which also contains metadata on the variables.

What data from the 2001 Census are available in the LS?

Data from the 2001 Census have now been linked to the LS database. Individual-level variables, including occupation, household and family variables and information on region, county and county district of usual address are available. The 2001 Census included new questions on religion, self-rated health, caregiving and a new household relationship question using a relationship grid. A revised question on education relating to all levels was asked. You can look at the 2001 variables in the data dictionary.

What geographical information is available in the LS? At what level can geographical analysis be carried out?

The LS covers individuals who are usually resident in England and Wales, in private households and communal establishments. The LS contains geographical information at each census and for events data. For each census, information was collected on address on census day and usual address one year before each census. Data on usual address are available in the LS at county district, county and regional levels for these time points. It is also possible to classify areas using area classifications, including deprivation indices and urban and rural indicators. Some variables using health administrative boundaries are also available.

The lowest level of geography allowed for research is county district level or groupings of wards of equivalent size. Issues of confidentiality are an important consideration at low geographical area levels, and it may not be possible to undertake analyses at these levels.

Geography variables available in the LS can be found by searching the data dictionary, and papers and publications on geographical themes can be found using the publications search facility.

Geography in the LS is a complicated subject and if you would like any more information or advice, please see the interactive online training module on geography or contact the Executive Officer at CeLSIUS.

Are there any confidentiality restrictions on the use of the LS data?

There are certain confidentiality restrictions on the LS, because of the types of data it contains. Individual level data can never be released from the LS. Also data that might identify individuals cannot be released. Data containing ethnic groups, occupations and geography, in particular, have to be treated with caution. A number of different outputs are available to users and these are described in the online training module on LS outputs.

How do I apply to use the LS?

All projects must be approved by the LS Research Board. An application form, which describes the project to be undertaken, how the LS will be used to contribute to the aims of the project and specifies the extract required, should be completed and sent to the LS Research Board. A Research Support Officer from CeLSIUS will be allocated to your project and will help you complete the forms, if you have any queries. The application process is described more fully in our step-by-step guide to using the LS.

Is there information available about linkage rates?

Linkage rates show the proportion of people at one census who are present at a subsequent census, taking into account deaths and embarkations. Linkage rates by various subgroups have been produced by the Office for National Statistics.

What form will the data be in?

Because of the confidentiality restrictions on the LS data set, it is not possible for users to have uncontrolled access to the data. Users are required to sign an Data Access Agreement before LS data can be released to them. Users can then receive data in a number of ways. They can receive cross-tabulations, frequencies and regression models for their chosen study population, which have been produced by a CeLSIUS support officer. They can also receive aggregated data sets, which they can use at their own place of work. Aggregated data sets contain counts of individuals for combinations of different variables. To maintain the security of the LS all data are encrypted before being sent out to users and the approved encryption softare is Safeguard PrivateCrypto. Users can download this software for free from the PrivateCrypto Web site. It may also be possible to go to the Office for National Statistics to work on an extract of the data set prepared by a CeLSIUS support officer. All outputs will be checked by CeLSIUS staff before they are released to users, so that they meet the confidentiality requirements. For more information on outputs, see the online training module on LS outputs.

Can I attach my own data to the LS?

If you are interested in looking at factors which vary by geographical area, for example environmental factors or deprivation indices, and you have some data which you would like to use with the LS, it may be possible to attach your data to the LS. You will need to contact CeLSIUS to find out whether this is an appropriate use of the LS.

Do I have to have my article cleared before publication?

Yes, it is necessary for all publications using LS data to be cleared by ONS before they are published. Details of the clearance process are given in our step-by-step guide to using the LS.

What other longitudinal studies are available that I can use?

If you find that the LS is not suitable for your research, there are other longitudinal studies for the United Kingdom. The Scottish Longitudinal Study includes data from the 1991 and 2001 Censuses as well as other sources, and a Northern Ireland Longitudinal Study has recently been launched. Information about other longitudinal studies available for research can be obtained from the Economic and Social Data Service.

Does the LS contain information on families and households?

The LS is a 1% sample of individuals of people usually resident in England and Wales. It also contains information on all people living with members of the sample (called LS members) at each census. Variables on family and household characteristics are available in the LS. For further information on families and households in the LS see "Researching households and families using the ONS Longitudinal Study" by A Brassett-Grundy (LS User Guide No. 20, PDF 902K) and the data dictionary.

Does the LS contain information on birthweight?

The LS contains information on live births, infant deaths and still births to sample mothers, and new births. Information on birthweight is available from 1976, although the proportion of births with birthweight recorded is low in the first few years. For more information, you should look at the data dictionary and Longitudinal Study 1971-1991: History, organisation and quality of data (LS Series No.7).

Can you look at migration in the LS?

Geographical information at region, county and county district level of usual address is available at each census. There is also information on usual address one year ago at each census and five years ago in 1971. It is, therefore, possible to track individuals from one census to another in England and Wales.

What events data does the LS contain?

Information is available on mortality, including cause of death, widowhoods, infant mortality and still-births, and fertility including live births to sample mothers and new births. There is also information on cancer registrations, embarkations, immigrations and re-entrants.

What should I do if I have any other queries?

If you have any further queries, please contact CeLSIUS (e-mail: or telephone: 020 7299 4634).

Last modified 1 March 2011