Executive summary

Why we carried out this assessment

ES.1 The Scottish prison population statistics provide granular, accessible, and insightful information about the Scottish prison population. The statistics have been published in their current form since 2020. They were developed to fill a long-standing gap left by the discontinuation of the previous National Statistics (in 2014). It is essential that they continue to be published to allow Scottish Government and the public to monitor trends in the Scottish prison population.

ES.2 Scottish Government asked the Office for Statistics Regulation (OSR) to assess the Scottish prison population statistics. This assessment follows a compliance check carried out in February 2021. In requesting this assessment, the statistics team at Scottish Government is demonstrating its commitment to produce statistics that meet the standards required of National Statistics and the Code of Practice for Statistics.

ES.3 Our assessment found widespread good practice in the production of these statistics. We have identified four actions for Scottish Government to fulfil in order for the Scottish prison population statistics to be designated as National Statistics. Once the statistics team demonstrates that these steps have been undertaken, OSR will recommend that the UK Statistics Authority designate the statistics as National Statistics.

Key findings

ES.4 The statistics team has an open dialogue with users and engages with them through a variety of means, including surveys, presentations, and workshops. These proactive user engagement activities have enabled the team to identify key users and stakeholders of the statistics, understand their needs, and develop the statistics. The team can build on this successful engagement by broadening the types of users it engages with.

ES.5 Scottish Government and the Scottish Prison Service (SPS) have formed an effective partnership to produce the statistics. Two recent developments are expected to support more coordinated and collaborative working. Scottish Government and SPS are currently reviewing the memorandum of understanding between the two organisations, and SPS recently recruited a new Head of Data and Analysis. The Head of Data and Analysis provides a much-needed boost to SPS’s analytical capacity and capability and will help facilitate knowledge sharing between SPS and Scottish Government.

ES.6 Granularity is one the key strengths of these statistics. Data are broken down by a range of demographic and other characteristics, including prison establishment and legal status, which is helpful for understanding changes in the prison population over time.

ES.7 The statistical bulletin is informative and engaging, with detailed and impartial commentary and visualisations that aid interpretation of the statistics. The team has developed an excellent interactive analytical tool. It promotes reuse of data and supports interpretation of the statistics by allowing users to explore the data themselves.

ES.8 At present, the Scottish prison statistics and data landscape is somewhat uncoordinated. In addition to the official statistics produced by Scottish Government, SPS produces its own quarterly performance report which covers similar areas to the official statistics. To enhance coherence and insight, and minimise the risk of undermining the official statistics, Scottish Government should work collaboratively with SPS to explore if they can produce more joined-up statistics about the prison population in Scotland.

ES.9 The team has successfully linked prisoner home address information with 2016 Scottish Index of Multiple Deprivation (SIMD) data to add insight on arrivals by deprivation. The team’s plans to link prison population data with data on a range of other topic areas, including education, health and drug use show ambition to maximise the value of the statistics. It supports our vision of a statistical system that makes data linkage the norm.

ES.10 The statistics are based on administrative data from SPS’s prisoner records system (PR2). Several users told us that the quality of the official statistics meets their needs. However, some users queried with us aspects of the PR2 system, such as outdated IT infrastructure and the level of quality assurance of data. Scottish Government is confident in the quality of the data used to produce the statistics. It told us that PR2 serves the functions it was designed for – understanding and managing the prison population – and that it accurately records information.

ES.11 The bulletin and technical manual are clear about the nature and limitations of PR2. To reassure users about data quality and demonstrate transparency about its quality assurance (QA) approach, Scottish Government should explain the strengths of the PR2 system and why it is confident in the quality of the data. It should also review its QA process and publish more-detailed information about data collection, checking and validation.

ES.12 Longitudinal analysis is essential for understanding the prison population. It allows the measurement of flows into and out of prison, changes in prisoner demographics, and changes in prisoners’ custodial ‘journeys’. The Cellwise method used to construct the statistics creates a longitudinal ‘spine’ from historic PR2 prison cell occupancy data and then adds a range of other information to this spine. The method is sound and well-explained; the technical manual gives a step-by-step account of the construction of the statistics. The bulletin outlines the differences between the Cellwise data and other sources of information about the Scottish prison population, which helps users understand the comparability and coherence of the statistics.

ES.13 Due to the way information is recorded on PR2 and the way the Cellwise dataset is constructed, there is uncertainty in the estimates. To help users interpret the statistics, the information about uncertainty should be expanded, by explaining the nature of the prison population estimates and the confidence intervals around the general population estimates.

ES.14 The team applies Reproducible Analytical Pipeline (RAP) principles to the production of the statistics, which supports robust quality management. Our main concern about the current setup is that there is only one statistician in the team with access to the data and sufficient knowledge to run the code. To improve the team’s resilience and ensure the process can be understood and used by multiple team members, the team should prioritise the development of documentation and coding skills.