Census Innovation at CeLSIUS
Lead Research Organisation:
UNIVERSITY COLLEGE LONDON
Department Name: Epidemiology and Public Health
Abstract
This project aims to develop two aspects of Census data.
1) Addressing the gap in provision with regard to access and utilising the most restricted access UK Census data (other than the longitudinal studies) by providing enhanced user information guidance, training and user support
2) Creation of a fake (impossible) longitudinal England and Wales dataset to enable users to explore the data, select variables and draft code for their analyses
Gap in provision
This currently exists with regard to support for using secure UK Census data other than the longitudinal studies which are currently supported by three organisations CeLSIUS in England and Wales, NILS-RSU in Northern Ireland and SLS-DSU in Scotland - collectively they form UKCenLS. Less restricted access versions of the data are currently well supported by the UK Data Service but there is no support for the most restricted access data sets other than limited user information and data storage and research clearance. CeLSIUS aims to further support two groups of data: secure origin-destination or 'flow' data (migration, commuting, student migration, and second residence sets) from 2011 and 2021/2, and de-identified individual and household microdata from 1961 to 2021.
This project seeks to assess feasibility and affordability of these potential new support services and provide the required user information guidance and training in particular for the 2021/2 data where none yet exists.
This service will support researchers who wish to use UK census 2021/2 migration and commuting and individual data for social science-led research, but also compare change over time.
CeLSIUS has considerable experience in supporting the user of the other restricted access census data and will ensure that no data that could identify an individual becomes public.
Creation of a fake longitudinal data set
Currently it is hard for users to know what variables are in the Office for National Statistics Longitudinal Study (ONS LS) and is getting harder with each Census. There are approximately 600 variables per Census and in some cases hundreds of categories for a variable.
The current solutions: a) ask CeLSIUS and/or ONS b) use the data dictionary c) look at the Census forms. It is hard for users to choose the best variable options when they are so many options. This means users may select the wrong variables for their project and then must reapply for any additional variables which causes delays and places administrative burden on ONS and CeLSIUS. Also we have users who never see the data set and we do analysis for them and no users ever see the full data set so they do not always know what is best to select.
We aim to create a individual level complete fake longitudinal data set to be openly available. This has imaginary people from 1971-2021 with impossible characteristics covering all options in the Censuses. This open data set will reduce burden on users and the user support team of the ONS LS. It will also be a useful tool for training.
1) Addressing the gap in provision with regard to access and utilising the most restricted access UK Census data (other than the longitudinal studies) by providing enhanced user information guidance, training and user support
2) Creation of a fake (impossible) longitudinal England and Wales dataset to enable users to explore the data, select variables and draft code for their analyses
Gap in provision
This currently exists with regard to support for using secure UK Census data other than the longitudinal studies which are currently supported by three organisations CeLSIUS in England and Wales, NILS-RSU in Northern Ireland and SLS-DSU in Scotland - collectively they form UKCenLS. Less restricted access versions of the data are currently well supported by the UK Data Service but there is no support for the most restricted access data sets other than limited user information and data storage and research clearance. CeLSIUS aims to further support two groups of data: secure origin-destination or 'flow' data (migration, commuting, student migration, and second residence sets) from 2011 and 2021/2, and de-identified individual and household microdata from 1961 to 2021.
This project seeks to assess feasibility and affordability of these potential new support services and provide the required user information guidance and training in particular for the 2021/2 data where none yet exists.
This service will support researchers who wish to use UK census 2021/2 migration and commuting and individual data for social science-led research, but also compare change over time.
CeLSIUS has considerable experience in supporting the user of the other restricted access census data and will ensure that no data that could identify an individual becomes public.
Creation of a fake longitudinal data set
Currently it is hard for users to know what variables are in the Office for National Statistics Longitudinal Study (ONS LS) and is getting harder with each Census. There are approximately 600 variables per Census and in some cases hundreds of categories for a variable.
The current solutions: a) ask CeLSIUS and/or ONS b) use the data dictionary c) look at the Census forms. It is hard for users to choose the best variable options when they are so many options. This means users may select the wrong variables for their project and then must reapply for any additional variables which causes delays and places administrative burden on ONS and CeLSIUS. Also we have users who never see the data set and we do analysis for them and no users ever see the full data set so they do not always know what is best to select.
We aim to create a individual level complete fake longitudinal data set to be openly available. This has imaginary people from 1971-2021 with impossible characteristics covering all options in the Censuses. This open data set will reduce burden on users and the user support team of the ONS LS. It will also be a useful tool for training.
Publications
Mastrosavvas A
(2025)
The Longitudinal Impossible Dataset: Helping Users Navigate the ONS Longitudinal Study
in International Journal of Population Data Science
Mastrosavvas A
(2025)
The Longitudinal Impossible Dataset: Helping Users Navigate the ONS Longitudinal Study
Mastrosavvas A
(2025)
The Longitudinal Impossible Dataset: Helping Users Navigate the ONS Longitudinal Study
Sizer A
(2025)
The ONS Longitudinal Study - opportunities for longitudinal research on the England and Wales population
in IASSIST Quarterly
| Description | The most significant achievements from the award were two fold. First the production of the Longitudinal Impossible Data Set (LIDS) - a free to use data set that allows users to create bespoke, artificial data extracts to familiarise themselves with data structures, plan their research project, and develop analytical code-all without accessing real ONS LS data Secondly support materials for other secure Census data were made available by CeLSIUS. https://www.ucl.ac.uk/population-health-sciences/epidemiology-health-care/research/ucl-research-department-epidemiology-public-health/research/health-and-social-surveys-research-group/studies/celsius/census-microdata-samples ONS took the decision not to make available secure flow data, so materials were produced for secure micro data. |
| Exploitation Route | The findings may be taken forward by the team to work with other secure data holders to produce similar data sets for training and coding. |
| Sectors | Government Democracy and Justice |
| Description | Initial steering meeting with the ONS 2021 Census Production team |
| Geographic Reach | National |
| Policy Influence Type | Contribution to new or improved professional practice |
| Description | Invited participant in ONS discussion - What are the new opportunities to use administrative and other data to help deliver a census? |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Impact | The discussions led into planning for future data needs |
| Description | Invited participation in Review of UKSA DEA researcher and research accreditation criteria |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Impact | The views discussed about how the accreditation criteria for researchers/projects using data collected under the DEA legal gateway can be improved will help the UK Statistics Authority team with their work |
| Description | Participant in three rounds of ESRC/MRC PRUK Delphi surveys entitled: "Reaching consensus on representativeness and coverage in longitudinal population studies" |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| URL | https://www.ukri.org/opportunity/understanding-coverage-in-uk-longitudinal-population-studies/ |
| Description | Submission of evidence to the Census 2031 topic consultation |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Impact | The National Statistician requested the meeting where I collated user views on topics. I added those to submissions from CeLSIUS and BSPS |
| URL | https://blog.ons.gov.uk/2026/03/04/putting-the-foundations-in-place-to-make-census-2031-a-success/ |
| Description | Submission to consulation on UK Statistics Assembly |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Impact | The event will be repeated followings its success. The National Statistician has arranged to meet NS to discuss a BSPS day meeting |
| URL | https://uksa.statisticsauthority.gov.uk/uk-statistics-assembly-2025/ |
| Title | New support services and documentation on census microdata samples, including the Census Microdata Finder tool |
| Description | New services and documentation were launched to support research use of census microdata samples. CeLSIUS now supports prospective user queries on 2011 and 2021 secure census microdata, providing guidance and feedback on research project applications and the application process. The CeLSIUS website now also hosts resources and information on all available census microdata samples with details on sample sizes, variables, metadata, and use cases. This includes the launch of an interactive table, the CeLSIUS Microdata Finder, which consolidates and signposts all available user support resources for each dataset across relevant domains, including ONS and UKDS. It also includes a copy of the online Project Accreditation Service for the SRS (PASS) form that familiarises prospective users with the information required. |
| Type Of Material | Improvements to research infrastructure |
| Year Produced | 2026 |
| Provided To Others? | Yes |
| Impact | Members of the team have began using the finder tool and the pass copy form to develop and support new research project applications |
| URL | https://www.ucl.ac.uk/population-health-sciences/epidemiology-health-care/research/ucl-research-depa... |
| Title | Longitudinal Impossible Data Set (LIDS) |
| Description | LIDS allows users to create bespoke, artificial data extracts to familiarise themselves with data structures, plan their research project, and develop analytical code-all without accessing real ONS LS data. LIDS is built entirely from publicly available ONS LS metadata sourced from the CeLSIUS data dictionary. Using this metadata, LIDS produces artificial data extracts that mirror the structure, variable names, table names, and coding schemes of the ONS Longitudinal Study. This enables users to work with data that behave like a real ONS LS extract but contain no actual personal information. The name 'Impossible Dataset' reflects an important characteristic: while LIDS uses plausible codes and structures, the values in each generated observation are randomly assigned and independent of one another. This means that artificial extracts produced through LIDS can represent substantively impossible or highly improbable scenarios-for instance, a person listed as retired well before retirement age or a death record dated before a person's birth. While this means LIDS cannot and should not be used for substantive research, it provides a realistic structure for data discovery, metadata exploration, research project development, code development, and training. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2026 |
| Provided To Others? | Yes |
| Impact | Interest from potential and current users: at the launch webinar an attendee said "seems like such a helpful resource having recently gone through the application process for a different secure dataset". Another said "we will get on this." Interest from other data owners: Meeting with Scottish Longitudinal Study team 6/2/26 - planning to submit grant application to extend to SLS led by NS Meeting attended by UK Data Service June 2025 interest in beta product - follow up meeting 13th March considering submission of grant application to extend to UKDS secure data led by NS |
| URL | https://www.ucl.ac.uk/population-health-sciences/epidemiology-health-care/research/ucl-research-depa... |
| Description | Meeting with National Statistician |
| Organisation | Office for National Statistics |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | Following a meeting with Sir Ian Diamond the National Statistician there has been a decision made to hold a BSPS day meeting taking about the future of population statistics |
| Collaborator Contribution | I arranged the meeting |
| Impact | Day meeting to be held May-July 2025 |
| Start Year | 2025 |
| Description | Meetings with Office for National Statistics |
| Organisation | Office for National Statistics |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We have illustrated the support we can provide to users of secure census micro data to ONS and they have said our work is 'crucial' |
| Collaborator Contribution | They have advised us on access to data and availability and content |
| Impact | LIDS data set https://www.ucl.ac.uk/population-health-sciences/epidemiology-health-care/research/ucl-research-department-epidemiology-public-health/research/health-and-social-surveys-research-group/studies/celsius/longitudinal-impossible-dataset info on secure microdata https://www.ucl.ac.uk/population-health-sciences/epidemiology-health-care/research/ucl-research-department-epidemiology-public-health/research/health-and-social-surveys-research-group/studies/celsius/census-microdata-samples |
| Start Year | 2024 |
| Description | Meeting with and presentation to the Scottish Longitudinal Study (SLS) team at the University of Edinburgh on the Longitudinal Impossible Dataset |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | This talk followed on from engagement with the SLS team at conferences, who expressed interest in adopting a similar tool for the SLS. This meeting and talk involved a detailed demonstration of the Longitudinal Impossible Dataset with an in-depth discussion on design and methodology, followed by a review of the suitability of SLS metadata. This has resulted in an ongoing collaboration to develop a LIDS for SLS. |
| Year(s) Of Engagement Activity | 2026 |
| Description | National Conference joint ONS / BSPS / CeLSIUS / UK Data Service meeting on Future of the UK Demographic System |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | The event includes talks from the UK national statistics offices and the UK Statistics Authority, We also canvassed participants for evidence for consultations on the 2031 Census (2025) |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://ukdataservice.ac.uk/events/the-future-of-the-uk-demographic-system-2025-07-10/ |
| Description | Talk at the 2024 BSPS conference Innovation in Census Support at CeLSIUS |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Paper presented to academic conference - strong interest from users in the innovation and useful feebback received |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.lse.ac.uk/international-development/research/british-society-for-population-studies/Asse... |
| Description | Talk at the British Society for Population Studies Annual Conference 2025 on the Longitudinal Impossible Dataset |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The talk covered the conceptualisation and methodology behind the Longitudinal Impossible Dataset (LIDS), including a prototype demonstration, and discussed use cases. This talk attracted particular interest by the Office for National Statistics (ONS), who praised LIDS' design and its potential to improve existing ONS LS metadata. It also attracted interest by the Scottish Longitudinal Study (SLS), kick-starting talks on developing a similar product. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.lse.ac.uk/international-development/research/british-society-for-population-studies/Asse... |
| Description | Talk at the Society for Longitudinal and Lifecourse Studies Annual Conference 2025 on the Longitudinal Impossible Dataset |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The talk covered the conceptualisation and methodology behind the Longitudinal Impossible Dataset (LIDS), including a prototype demonstration, and discussed use cases. This talk attracted particular interest by international researchers, receiving strong feedback. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.slls.org.uk/events/2025-slls-annual-international-conference |
| Description | Talk at the UK Census User Conference 2025 on the Longitudinal Impossible Dataset |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | The talk covered the conceptualisation and methodology behind the Longitudinal Impossible Dataset (LIDS), including a prototype demonstration, and discussed use cases. This talk attracted particular interest by data services practitioners, including the UK Data Service, who expressed interest in adopting similar innovations for managed data products. The talk also resulted in collaboration for the publication of a UKDS Data Impact Blog on LIDS. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://ukdataservice.ac.uk/events/uk-census-user-conference-2025/ |
| Description | UK Data Service Impact Blog on the Longitudinal Impossible Dataset |
| Form Of Engagement Activity | Engagement focused website, blog or social media channel |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | A blog on the Longitudinal Impossible dataset has been published on the UK Data Impact blog. The blog is targeted at explaining how the tool can be used, its methodology, and use cases in accessible way to wider audiences. The blog enjoyed strong coverage on social media platforms and newsletters, with positive commentary on its usefulness and design. |
| Year(s) Of Engagement Activity | 2026 |
| URL | https://blog.ukdataservice.ac.uk/longitudinal-impossible-dataset/ |