A data driven approach to transforming population and migration statistics

Main Article Content

Vicky Field
Published online: Nov 8, 2019


The Office for National Statistics (ONS) is transforming the way we produce population and migration statistics, to a system that is led by administrative data.


Population and migration statistics underpin a wide variety of other statistics and inform a vast range of decisions, including pensions forecasting and provision of local services. These statistics are also used to help inform public debate, it is therefore essential that these statistics are accurate and timely. Until now the census has formed the cornerstone of these statistics, with updates from other surveys and some administrative data. Enabled by new data sharing powers in the Digital Economy Act (2017), we now have the opportunity to make use of more data: and this is essential to better understand our rapidly changing population at both national and local levels, and the wider policy impact and context.


We know that there is no single, comprehensive data source that tells us everything about the population. Therefore, we are developing ‘data-driven rules’ to use as part of a future system. This focuses on identifying the strengths of individual data sources and integrating them to provide richer understanding of how our population is changing.


This approach will also allow us to be flexible in implementing different definitions to understand sub-groups of the population. For example, the daytime population to understand the impact that the increasingly more mobile population has on different services.


We have undertaken research progressing administrative data-based population estimates, linked data to inform our understanding about migration patterns, reflecting the changing population and the impact that this has on society. The session will provide the latest on the research that ONS has carried out into the potential of administrative data in supporting and delivering a new system that can offer more responsive, frequent and timely insights into our society.


The Office for National Statistics (ONS) is transforming the way we produce population and migration statistics, to a system that is led by administrative data.

Population and migration statistics underpin a wide variety of other statistics and inform a vast range of decisions, including pensions forecasting and provision of local services. These statistics are also used to help inform public debate, it is therefore essential that these statistics are accurate and timely. Until now the census has formed the cornerstone of these statistics, with updates from other surveys and some administrative data. Enabled by new data sharing powers in the Digital Economy Act (2017), we now have the opportunity to make use of more data: and this is essential to better understand our rapidly changing population at both national and local levels, and the wider policy impact and context.

We know that there is no single, comprehensive data source that tells us everything about the population. Therefore, we are developing ‘data-driven rules’ to use as part of a future system. This focuses on identifying the strengths of individual data sources and integrating them to provide richer understanding of how our population is changing.

This approach will also allow us to be flexible in implementing different definitions to understand sub-groups of the population. For example, the daytime population to understand the impact that the increasingly more mobile population has on different services.

We have undertaken research progressing administrative data-based population estimates, linked data to inform our understanding about migration patterns, reflecting the changing population and the impact that this has on society. The session will provide the latest on the research that ONS has carried out into the potential of administrative data in supporting and delivering a new system that can offer more responsive, frequent and timely insights into our society.

Article Details