Office for Statistics Regulation

The Office for Statistics Regulation (OSR) is the regulatory arm of the UK Statistics Authority, a body established by the Statistics and Registration Service Act (2007). We are independent from government Ministers. We are separate from producers of statistics, including the Office for National Statistics (ONS). In line with the Statistics and Registration Service Act our principal roles are to:

• set the statutory Code of Practice for Statistics
• assess compliance with the Code of Practice
• award the National Statistics designation to official statistics that comply fully with the Code of Practice
• report any concerns on the quality, good practice and comprehensiveness of official statistics

Statistics are an essential public asset. We aim to enhance public confidence in the trustworthiness, quality and value of statistics produced by government. We do this by setting the standards they must meet in the Code of Practice for Statistics. We ensure that producers of official statistics are held to account and uphold these standards by conducting assessments against the Code. Those which meet the standards are given National Statistics status, indicating that they meet the highest standards of trustworthiness, quality and value. We also report publicly on system-wide issues and on the way that statistics are being used, celebrating when the standards are upheld and challenging publicly when they are not.

An important part of OSR’s purpose is to protect the role of statistics in public debate. This is because, for statistics to serve the public good, it is not enough that they are collected and published in appropriate ways. They must also be used appropriately. Failure to use statistics appropriately could lead to people being misled about aspects of society and policy; and could also lead people to lose confidence in official statistics. Both outcomes – people being misled and a loss of confidence – would mean that statistics were not serving the public good.

Our philosophy

In a world of abundant data, we want people to have confidence in statistics produced by the public sector. Our vision and mission are underpinned by the three pillars set out in the Code of Practice for Statistics:

• Trustworthiness is a product of the people, systems and processes within organisations that enable and support the production of statistics and data. Trustworthiness comes from the organisation that produces statistics and data being well led, well managed and open, and the people who work there being impartial and skilled in what they do.
• Quality means that statistics fit their intended uses, are based on appropriate data and methods, and are not materially misleading. Quality requires skilled professional judgement about collecting, preparing, analysing and publishing statistics and data in ways that meet the needs of people who want to use the statistics.
• Value means that the statistics and data are useful, easy to access, remain relevant, and support understanding of important issues. Value includes improving existing statistics and creating new ones through discussion and collaboration with stakeholders, and being responsible and efficient in the collection, sharing and use of statistical information.

Official Statistics and the Nolan Principles

We see the Nolan Principles as being central to the standards that we expect of statistics producers and have specifically enshrined the Principles in the Code of Practice for Statistics. The first practice in the Code states:

“Everyone that works in organisations producing official statistics should handle and use statistics and data with honesty and integrity, guided by established principles of appropriate behaviour in public life.”

The Code’s Foreword from the Chair of the UK Statistics Authority specifically references and underscores the Nolan principles (see the annex which shows how the Code relates to the seven propriety principles).

There are some key areas in official statistics in which the Nolan Principles are vital:

• equality of access – ensuring openness, that the information being used by the Government in public statements is available for the public
• orderly release – demonstrating honesty, integrity and objectivity in the way statistics are used within statistics producer bodies and presented in news releases, ministerial statements and policy documents and reflects our expectation of ministers and public officials, such as communications and policy officials, as well official statistics producers
• leadership – demonstrating the Code standards (including the Nolan Principles) as a leading example in the use of data and statistics, advocating that others demonstrate appropriate use too and challenging when they fall short

We see effective statistical leadership as requiring individuals at all levels and across professions to stand up for statistics and champion their value. Where there is strong statistical leadership, there is the confidence to engage openly both outside and within government and to identify and address society’s key questions with courage and insight. The Coronavirus (COVID-19) pandemic has demonstrated authoritative statistical leadership in very challenging circumstances, which has helped to ensure that statistical evidence is at forefront of decision making and debate.

In our recent review of statistical leadership (to be published shortly), we saw examples of analysts championing orderly release and equal access to statistics and challenging inaccurate interpretation or inappropriate use of statistics, all of which are key to maintaining public confidence in statistics and in analysts themselves. Here are two of the examples we identified:

• Some analysts, such as those at the Department for Transport, have made the case for more orderly release of data related to COVID-19, improving transparency to the public, while others, such as those in the Northern Ireland Statistics and Research Agency (NISRA) proactively communicated with the press about statistics related to COVID-19, to ensure they were interpreted appropriately.
• Our Assessment of ONS UK employment and jobs statistics commended the statistical team for challenging inappropriate use of the employment and jobs statistics and for publicly defending the published statistical estimates. These statistics are key economic indicators, and vital for understanding the patterns and dynamics of the UK labour market: it is therefore essential that they are not used in a misleading way.

As the regulatory arm of the UK Statistics Authority, OSR has responsibility for maintaining and promoting the Code of Practice for Statistics across official statistics producers in the UK. Our Policy and Standards function provides training and guidance materials to educate and support both the regulators within OSR and official statistics producers. We work closely with the Best Practice and Impact Division of the Office for National Statistics which provides guidance and training for the Government Statistical Service.

Advocating the standards beyond official statistics

When the Code of Practice for Statistics was published in 2018, we committed to promoting the pillars of Trustworthiness, Quality and Value across government and beyond. We see these as universal standards that can guide all analysts. We promote the voluntary application of the Code pillars and have established a community of practice for analysts and organisations with an interest in applying the pillars.

One of the most exciting developments over 2020 was the increase in the number of organisations choosing to voluntarily apply the pillars to published analytical outputs, such as management information, when they have no statutory obligation to do so. We have seen a range of organisations, including government departments, take up voluntary application. The Department for Environment, Food and Rural Affairs; the Department for International Development; HM Courts & Tribunal Service; the Scottish Government; the Department for Work and Pensions; the Ministry of Housing, Communities and Local Government; the Cabinet Office; HM Treasury; and Qualifications Wales have all already elected to apply the Code pillars to some of their data and analysis that are not official statistics. We have also noted willingness by the UK Government to voluntarily apply the pillars of the Code when publishing management information and data related to COVID-19 in a range of cases.

The fact that these organisations have voluntarily applied the pillars of trustworthiness, quality and value is one of the strongest testaments to their power: we believe the increasing application of these pillars reaffirms producers’ awareness of and willingness to address the importance of building public confidence in statistics. We would like to see more government organisations embracing voluntary application of the Code for analytical outputs beyond official statistics, especially when these outputs are informing decisions that are of high public interest.

We want to encourage adoption of the Code philosophy as widely as possible. We are delighted that, alongside government organisations, other organisations outside of official statistics have applied the Code pillars, such as a regulator – the Financial Conduct Authority; an independent commission – the Social Metrics Commission; an independent charity providing advice to students – Universities and Colleges Admissions Service (UCAS); local government bodies in the Greater London Authority; and an international statistics body – Statistics Jersey. A full list of organisations that have made a public commitment to applying the pillars to their statistics analysis or data in a statement of compliance is available on our website.

OSR is responsible for undertaking monitoring to identify issues and investigating concerns raised with the UK Statistics Authority. We use our voice to stand up for statistics and to represent the public, reporting publicly where we have concerns and highlighting good practice. Published or private correspondence will usually come from the Director General for Regulation. When the issue relates to broader political use, especially by Ministers and elected representatives, the Authority Chair will respond.

When considering issues around the use of statistics we recognise that the context is important. We do not seek to be a mediator in political debate but will stand up for appropriate use of statistics. We will intervene if:

• official statistics are shared before publication
• the advice of professional statisticians is ignored, or
• official statistics or data used in a document or statement are presented in such a way that, in the Authority’s opinion, they are likely to mislead the public or undermine the integrity of official statistics

In considering whether documents or statements are liable to mislead, we judge whether, on a question of significant public interest, the way statistics are used is likely to leave a reasonable person believing something which the full statistical evidence would not support.

While our statutory remit covers ‘official statistics’, we take a broad view of what falls within our scope. For many who see the publication of numerical information, the distinction between ‘official statistics’ and other data may seem artificial. As a result, we consider issues that may be perceived as official statistics, whether or not they are official statistics.

On occasion we will informally consider issues around production or use of data by organisations outside government, for example if an issue is raised with us in relation to an organisation that has voluntarily adopted the Code of Practice, or there are concerns around local authority data which are of national significance.

We consider the use of statistics and data by members of governments across the UK. We also expect members of the opposition in each nation to adhere to the same standards we expect from ministers when quoting statistics in public debate.

We reviewed our interventions policy and published a revised version in draft form, inviting feedback (ending 18 March 2021).

Having a published, public-focused outcomes-based behavioural code of conduct, that informs public sector professionals’ development, identities and competencies, is a model that could work to support positive ethical behaviour in other public bodies and for other professional groups too.

We find that providing a clear demonstration of our standards in practice, taking an empathic and cooperative approach to regulation, and modelling the behaviours we are seeking to achieve, leads to constructive engagement and application of the standards we uphold.

The Code pillar of Trustworthiness reflects each of the Nolan principles, while Quality and Value also embody ‘Openness’. The list below highlights specific practices in the Code of Practice for Statistics and the corresponding aspect of the Nolan Principles:

• ‘selflessness’ – working for the public good (T1.2) (and reiterated with our vision that ‘statistics should serve the public good’, as well as the Statistics and Registration Service Act 2007)
• ‘integrity’ and ‘honesty’ – handling and using data and statistics with honesty and integrity (T1.1), free from conflicts of interest (T1.2)
• ‘objectivity’ – presenting statistics impartially and objectively (T1.4), (T3.8)
• ‘openness’
  • making public commitments about public engagement and quality management (T4.1, T4.5),
  • being open about business priorities and progress (T4.2),
  • and about areas for improvement (T4.6),
  • about how information will be managed and protected (T6.1, T6.2),
  • providing clear rationale for decisions about data and methods and any changes (Q1.5, Q2.2, Q2.3, Q2.4, Q2.5)
  • and clear explanations about the quality of statistics (Q3.1, Q3.3),
  • maintaining an open dialogue and listen to views (V1.4),
  • giving feedback to stakeholders and being open about how needs can and cannot be met (V1.5)
• ‘accountability’ – statistics producers are accountable for their actions in preparing and releasing official statistics (Code annex), emphasised for statistical leaders (T2.3) and regarding protecting personal data (T6.4), and the role descriptions of Chief Statisticians and Lead Statisticians (Code glossary)
• ‘leadership’ – ensuring independent decision making and statistical leadership (T2), including actively advocating the standards of the Code (T2.2), challenging the misuse of data and statistics (T2.5), and reporting any concerns around professional independence (T2.7)