A step-by-step guide to using the LS

1. Formulate your research question

What are you studying? Who will your sample be? What period would your research cover?

2. Is the LS the best data source for your research?

If you haven't already read about the ONS Longitudinal Study, you should do so. You should also consult the census forms if you are planning to use LS census variables:

  • Were the questions you are interested in asked in the years you want to study?
  • Were they asked of the age group you want to study?
  • If the responses were in pre-coded categories, will these categories meet the needs of your study?

You could also use CeLSIUS' data dictionary to check the categories in the variables you hope to use. Also, CALLS-Hub have a data dictionary that crosses all UK LS'. 

If you have any doubts about the suitability of the LS for your research contact us. If the LS is not for you, we might be able to suggest alternative sources of data. 

You should also review existing work on your subject that has used LS data, by looking at current and past projects as well as at our list of research outputs.

3. Study our online training

We have developed ten online training modules on: 

  • Analysing LS data (includes Poisson modelling and relative survival)
  • Defining a study population
  • Ethnicity
  • Events (includes births, deaths, cancer registrations and widow(er)hoods)
  • Fertility rates
  • Geography
  • Households and families
  • LS outputs
  • Mortality
  • Socio-economic status

These modules provide information on the variables available, suitable research designs and also give indicators of sample sizes. You can get further ideas by looking at our downloadable tables.

4. Contact CeLSIUS

Unless you are based outside the UK or in the private sector, you should be eligible for support from CeLSIUS (the service is free to the user, being funded by the Economic and Social Research Council). You should contact us - we will discuss your research question and your timescale, and pass your request on to a Support Officer who will guide you through the subsequent processes and make sure you get the best data for your research question. If you require one or two straightforward tables from the LS, either to establish whether the LS is likely to be useful, or to provide some background information, we can arrange this with a minimum of formality. 

If you are based outside the UK or in the private sector, please contact the LS team at the Office for National Statistics (ONS): LongitudinalStudy@ons.gsi.gov.uk.

5. Apply to use the LS

In order to ensure the confidentiality of individuals in the LS data sample, researchers must:

  • apply for Researcher Accreditation; and
  • submit a Research Project Proposal.

Researcher Accreditation

All LS researchers must hold ONS Researcher Accreditation, which involves meeting certain criteria and then making an Accredited Researcher Application (Word).We recommend that you first send your application to us by email: celsius@ucl.ac.uk so that we may help you to complete it to the standards required by ONS. When ONS have approved your application, they will invite you to attend a Safe User of Research data Environments (SURE) training course at ONS. Upon completion of this training, you will be asked to sign an Accredited Researcher Declaration (PDF). ONS Researcher Accreditation lasts for a period of five years.

Please note:

  • everyone named on a Research Project Proposal form (see below) must become an Accredited Researcher and must undergo a day's training, whether or not they intend to visit the VML
  • CeLSIUS LS user support officers will not be allowed to release any Intermediate Outputs for a project until everyone named on it has been trained

Submitting a research project proposal

To use LS data, Accredited Researchers must submit a Research Project Proposal (Word) and an LS Supplementary Form (Word) to the ONS Microdata Release Panel via celsius@ucl.ac.uk.

Contact celsius@ucl.ac.uk at any point for assistance with your application.

At the present time we estimate that from submission of your application to CeLSIUS to full and final approval you should allow six to eight weeks.

The ONS will contact you to inform you of your project's approval and will ask you to complete a Controlled Access Security Operating Procedures (SyOPs) and Researcher Data Access Agreement (DAA) form, which they will forward to you by email.

6. Perform analyses

A CeLSIUS Support Officer will construct the dataset for your research (and amend it if necessary as your study proceeds). The dataset will be held in a secure system which can only be accessed from the Virtual Microdata Laboratory (VML) areas in ONS offices; these are situated in London (Pimlico), Hampshire (Titchfield) and Wales (Newport). 

One way of analysing your data is to send code (e.g. in STATA, SPSS or SAS) to be run in your absence, or discuss with CeLSIUS the outputs that you require (perhaps constructing specimen tables or models) and we will write and run code for you. Another option is to visit a VML lab yourself and analyse your own data. Please always try to book a lab visit in advance in case the VML is not available.

A further possibility is to specify an aggregated dataset (which will have a limited number of values) to be released for you to analyse at your place of study/work; see dataset on survival for an example. Individual-level datasets will never be released.

7. Receive Intermediate Outputs from CeLSIUS

When you want research outputs to leave the secure system in the VML, perhaps to work on them on your own computer or to show them to other Accredited Researchers on the same project, they will be referred to as Intermediate Outputs. To maintain the security of the LS all Intermediate Outputs are checked by a Support Officer and encrypted before being emailed to users. 

Intermediate Outputs must be stored at the location you specify in section 3 of the LS Supplementary Form and can only be shown to Accredited Researchers on the same project. Furthermore, they cannot be shared with researchers outside the UK.

8. Seek Final Output Clearance for results to be made public

When you want to disseminate your LS results beyond your project team you must obtain Final Output Clearance from the Longitudinal Study Team at ONS.

The process for clearing final outputs reduces the risk of disclosure and ensures that the LS is properly described. Key criteria include:

  • Results aggregated to a minimum cell threshold. ONS asks that in results from which a count of individual persons could possibly be calculated - e.g. percentages, or graphs based on percentages - that count is 10 or more. However, ONS may consider giving clearance to results which do not meet this criterion, if there is a scientific justification.
  • The LS is described correctly. Standard descriptions are available.
  • 'Source: ONS Longitudinal Study' is added to tables and figures, where appropriate.
  • Results appreciate that the LS includes data for England and Wales only.

Final outputs may be either reports, journal articles, presentations or abstracts, or simply a set of results which are destined to be worked up as any of these. Allow 5 working days for final outputs clearance although many outputs are cleared more quickly than this. Complete a Final Output Clearance Form and send it with a copy of your work to us.

Once your final output has been cleared for public release you may disseminate it a number of times without resubmitting it for clearance, as long as no new results are included. Your cleared Final Outputs are given a clearance number which you should cite in your publications. You are asked to acknowledge the support of CeLSIUS and ONS in your publications and include a disclaimer. We have a suggestion below:

"The permission of the Office for National Statistics to use the Longitudinal Study is gratefully acknowledged, as is the help provided by staff of the Centre for Longitudinal Study Information & User Support (CeLSIUS). CeLSIUS is supported by the ESRC Census of Population Programme under project ES/K000365/1. The authors alone are responsible for the interpretation of the data."

We also ask researchers to note that all statistical results remain Crown Copyright, and should be acknowledged either as such and/or as "Source: ONS". 

The following copyright statement should be featured along with the above acknowledgement:

"This work contains statistical data from ONS which is Crown Copyright. The use of the ONS statistical data in this work does not imply the endorsement of the ONS in relation to the interpretation or analysis of the statistical data. This work uses research datasets which may not exactly reproduce National Statistics aggregates".

9. Delete all Intermediate Outputs

When your project is complete you should delete all Intermediate Outputs from your computer.

Copies of your output files will be archived by ONS and retrievable upon request.  

Page last modified on 02 aug 16 13:53 by Joanne Tomlinson