CSPS Data Processing Companion
A companion to processing published data and results from the Civil Service People Survey
Welcome
This companion outlines and documents the approach taken to approach taken to process data from the UK government’s Civil Service People Survey into a set of harmonised datasets that can be easily reused.
The harmonised data is available in the csps-data repository on Github. Specific documentation about the data is available in here.
Note that the harmonised People Survey data and this companion book are not official products of the UK government.
The harmonised data is derived from the official data published by the Cabinet Office. While efforts have been taken to ensure the accuracy and quality of the harmonised data, it is presented as-is and without warranty.
This companion book has been derived from information on the methodology of the survey published by the Cabinet Office and the personal knowledge of the author about the workings of the survey.
Companion structure
The structure of this companion is intended to (roughly) follow the structure and workflow taken by the R code in the csps-data repository.
Introduction: provides a general introduction to the companion and a high-level outline of the approach to processing the People Survey data.
Glossary of terms and concepts: provides a glossary of key terminology and concepts used throughout the companion, including terminology/concepts specific to the People Survey and the data processing as well as some terms and concepts relating to the UK Civil Service more generally.
Technical set-up: this part of the companion discusses general technical approach to the data processing, including coding and the software/packages used, the source data and the bespoke helper functions that have been written to assist the different stages of the data processing project.
Developing harmonisations: this part of the companion discusses and documents the approach taken to developing a harmonised set of identifiers the enable the processing of the People Survey data.
Extracting data: this part of the companion discusses and documents the approach taken to extracting the raw data from the People Survey publications.
Processing and harmonising data: this part of the companion discusses and documents the approach taken to standardising the raw data using the harmonised identifiers.
Data dictionaries: this part provides technical documentation of the output data files resulting from the processing stage.
Appendices: this part provides additional materials.
Colophon: the about page provides information about the development of this companion/website, accessibility, copyright and legal disclaimer. The website’s privacy policy is provided separately.
About the Civil Service People Survey
The Civil Service People Survey is is the annual employee attitudes survey that has carried out across the UK Civil Service since 2009. It is an important management tool for managers and leaders working within in the Civil Service. It is also a useful tool for external parties that hold senior officials and government ministers to account for the leadership and management of the Civil Service.
Copyright and licensing
This companion; the re-processed People Survey data and associated metadata; and, the software code written to process the data are copyright of Matt Kerlogue (2026).
This companion itself and re-processed data are licensed under the Creative Commons Attribution License 4.0 (CC-BY-4.0). While the the software code is licensed under the MIT License.
The raw data from the People Survey is Crown Copyright, licensed under the Open Government Licence 3.0
The recommended citation for this companion is:
Kerlogue M (2026) CSPS Data Processing Companion, https://mattkerlogue.github.io/csps-data/
The recommended citation for the re-processed data is:
Kerlogue M (2026) Civil Service People Survey harmonised datasets, https://github.com/mattkerlogue/csps-data
Read more on copyright, licensing and attribution.
Statement on AI
This companion and the data processing it documents have not been produced using artificial intelligence.
The author supports the Creative Commons’ CC Signals initiative. For this work the ‘Credit + Open’ signals apply, that is any use of this material by an AI-system appropriate credit/attribution should be given (as per the CC-BY license), and that the AI-systems used should be open models/ systems.