A million people in England and Wales have been tracked through censuses and life events for over 40 years, and this project keeps that data accessible to researchers. The Office for National Statistics Longitudinal Study is the UK’s largest nationally representative dataset of its kind, but using it requires navigating strict security and privacy rules. CeLSIUS provides the expert support—helping researchers design approved projects, analyse anonymised data, and publish results that cannot identify individuals. Without this unit, the data would remain locked away, and researchers would lose the ability to ask questions that require decades of linked records. If the project succeeds, it will allow researchers to continue uncovering how employment, housing, fertility, migration, and health interact across generations. For example, studies can show how economic status affects cancer survival, or how divorce patterns shift housing tenure over time. The 2021 census will extend the dataset to cover 50 years, making these long-term comparisons even more powerful. This is fundamental social science infrastructure—it does not produce immediate fixes, but it quietly underpins evidence for policies on health, housing, and inequality that affect millions of people.
View original technical description
CeLSIUS is a research support unit that enables research using the Office for National Statistics (ONS) Longitudinal Study for England and Wales- the largest nationally representative longitudinal dataset in the UK. Longitudinal studies follow the lives of individuals over a long period of time, showing us how people are affected by changes in society. The ONS Longitudinal Study contains the linked census data and some life events data of approximately one million sample members, collected over 40 years. This service is free to the user. The sample comprises people born on one of four selected dates of birth and therefore makes up about 1% of the total population. The sample was initiated at the time of the 1971 Census, and the five dates were used to update the sample at the 1981,1991 2001 and 2011 Censuses and in vital event registrations and registration of cancer. Thus, the ONS LS represents a continuous sample of the population of England and Wales, rather than a sample taken at one time point only. Information is also included for all people living in the same household as the ONS LS member whilst they live in the same household with the sample member. Full ONS LS members enter the study through birth on one of the four dates and immigration and existing members leave through death and emigration. The four dates are known only to a very small number of researchers based in ONS and the data is analysed in anonymised form and all results are published so that no one could be identified from them. To use the data the user must have an approved project and be an approved researcher. All research carried out must have public benefit. What type of research does CeLSIUS support: Associations between census data and event data For example: studies of associations between employment status and mortality, between economic status and cancer registrations, or between socio-economic factors and fertility; and survival analysis of mortality by area deprivation. Changes over time between censuses For example: analysis of patterns of retirement migration; studies of the effects of divorce and remarriage on housing tenure; or comparison of changes in education, employment and migration between different decades. Changes over time between event data sets Studies of changes in birth spacing or associations between fertility and cancer survival. Changes over time in population and sub groups This is especially useful for studies of ethnic or geographical factors. This project will continue to provide users with support in using the data and enable research to be carried out between 2020 and 2025. The 2021 census data when added will extend the data set to cover 50 years.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know