Statistical Practices

‘Truth surge’: celebrating the success of statistics

“After the fears about post truth, we’ve now got the truth surge”.

So said Rupert McNeil, Civil Service Chief People Officer, to me at an event to launch the UK Statistics Authority’s consultation on the new Code of Practice for Statistics last summer.

We’ve now published the new Code itself. And I want to return to Rupert’s idea of a truth surge in the context of one of the great unsung features of the Civil Service. At the same time, I want to celebrate statistics as one of our quiet successes – and explain why we shouldn’t be so quiet about it.

We talk a good deal about the roles of the Civil Service – providing sound and honest policy advice to ministers, ensuring the public receive excellent services, and delivering value for taxpayers’ money.

There’s another crucial role that we talk about less: providing high quality and trustworthy data and statistics into the public domain.

These statistics are a crucial building block of how people make decisions about the world: for businesses, on where and how to invest, and which markets to develop; for individuals, on where to live and where to send children to schools; and for communities, on how to improve the quality of local life.

At the Office for Statistics Regulation all our work starts from recognising that statistics are a public asset. They are the lifeblood of democracy. And, as Anthony Hilton put in an Evening Standard article, they are as essential to public life as physical infrastructure like water or electricity.

The quiet triumph I want to celebrate is the capacity of the Civil Service to provide these clear, trusted data and official statistics to the public, regardless of the political colour of the party running government. These statistics cover a vast range of activity, from the health of the population, to the number of households below average income, via the performance of schools, the quality of the natural environment, and the disparity in outcomes between different groups in society.

Life and death, war and peace, crime and punishment – all human life is here. And it’s done with the rigour, integrity, and competence that are the hallmarks of a brilliant Civil Service.

Many countries would struggle with this. They only recognise as official statistics the data produced by their independent statistical offices (the counterparts of the Office for National Statistics – ONS).

So in many countries there are two or three providers of official statistics. Here there are over 150. Elsewhere in the world, the idea that a department run by an elected minister could produce statistics to the same standard as an ONS-like body, would be hard to imagine. In the UK, with our strong institutional framework for an impartial Civil Service, we take it as read.

It’s a testament to the strength of Civil Service values through the professionalism of individual civil servants and of their departments and agencies as institutions. As such, this reliable provision of statistics is part of the fabric of sound public administration.

This hasn’t happened by accident. It’s the result of the accumulated experience of generations of civil servants – statisticians, other analysts and policymakers.

The Code of Practice for Statistics captures this accumulated experience – it’s the go-to guide for any public organisation publishing statistics.

So why do I think this shouldn’t be a quiet success anymore?

We live in era of fear, of post-truth, spin and filter bubbles; where stories abound of fake news. It’s also a world of increasingly abundant data – but where it can be harder to sift the reliable from the unreliable.

In this world of scepticism, the ability of the Civil Service to provide statistics that are trustworthy, of high quality and publicly valuable is very important – to government and to society.

That’s why we have redesigned the Code of Practice to focus on the three pillars, or outcomes, Trustworthiness, Quality and Value, the core foundations of public confidence. It’s why we emphasise statistics not as an arid or technical subject but as a public asset and the lifeblood of democracy. The refreshed Code of Practice for Statistics can help you use data and statistics appropriately, whether you are working in policy, operations or statistics and analysis, view it here https://osr.statisticsauthority.gov.uk/code-of-practice/

And it’s why Rupert McNeil is right: we need a surge. We need to shout from rooftops that statistics are worth defending as one of the most crucial functions of government.

So, we think our new Code is not just the foundation of public confidence. It’s more than this: it is a celebration of statistics as one of the key achievements of the British Civil Service.

End of Code consultation – reflections on our road trip

It has been great to get out and about to speak about the draft Code of Practice for Statistics over the past few months as we ran over 30 sessions. Our team has covered over 4000 miles all around the UK since the start of the consultation in July, visiting many departments and agencies that produce official statistics. We’ve also met a wide range of stakeholders – some working in other areas of analysis and data, plus others outside of government but with a keen interest in statistics.

The consultation closes today – 5 October – and now the work begins to reflect on all the feedback we have received. It has been terrific to see the genuine enthusiasm for the Code and its importance in setting standards. We strongly feel the responsibility in ensuring that the Code clearly sets out these standards, supported by guidance to show what it looks like to comply with the Code.

The road show seminars reminded us of the need for the Code to reach everyone in producer organisations – to ensure that everyone understands their individual responsibilities. This becomes essential in dealing with pre-release access, and other aspects of orderly release such as releasing at the standard time of 9.30am. Other aspects of sharing data and statistics are of big concern to analysts – from providing low quality data under Freedom of Information legislation to questions about sharing data with colleagues working on modelling prior to publication. The use of worked examples on our website, alongside the Code, will go a long way in helping to support understanding of how the Code applies in different situations.

We have also spoken about our wider ambition for the Code. We see its principles as having universal application with all kinds of data, being a useful guide particularly when publishing data that are important in helping to inform users or supporting them when making decisions. The audience at the Code seminars suggested some challenges that we will face as a regulator in managing voluntary compliance but also identified some very real opportunities.

Overall we found strong support for our proposed framework of ‘Trustworthiness, Quality and Value’ from those involved in producing official statistics. But we also heard from some who found the concepts to have a degree of overlap – highlighting that good quality and relevant statistics lead to trust. Under the proposed framework, it is essential that those producing statistics demonstrate why they deserve public confidence and why their statistics can be trusted.

“…it is essential that those producing statistics demonstrate why they deserve public confidence and why their statistics can be trusted.”

We are grateful to everyone who attended one of our sessions for being so willing to hear about the Code and to participate in discussions. We hope to be able to continue the conversations once we have published the refreshed Code, to support all those involved in publishing official statistics in understanding what it means for them in their role, as well as promoting its wider application.

Our next steps are to review the consultation responses and all of the feedback we have received throughout the consultation period. We will be publishing a response that summarises the feedback, including how we plan to incorporate it in the final version of the second edition of the Code of Practice. Do keep an eye out for future blog posts to stay updated on the latest developments.

Happy Families?

More than the sum of the parts: the role of families of statistics in supporting insight and innovation

In last year’s Code of Practice stocktake, we outlined the idea of ‘families’ of statistics. In this blog, I want to bring out some of the ways that ‘families’ support the way we are thinking about statistics as an essential public asset.

What do we mean by families of statistics?

The traditional way of publishing statistics reflects the way that the underlying data are collected – with each source being published as soon as the statistics are deemed ready. This gets new information into the public domain quickly, supporting decision makers and democratic debate.

But it can lead to the piecemeal release of statistics, a deluge of information that can be hard to interpret coherently. It can make it hard for the user to take a step back and ask “what is this new information telling me?”

Let me illustrate what we mean by ‘families’ of statistics through two examples – international migration, and roads.

As the diagram below shows, statistics about different aspects of international migration are drawn from a range of surveys and administrative sources and produced by several organisations across the UK. Each set of statistics is useful in its own right but the value of this ‘family’ is maximised when the statistics are brought together so that they shed light on the questions that are important to society. Indeed, ONS does bring several of the statistical sets together, in its Migration Statistics Quarterly Report.

And again, many organisations produce statistics, numerical information and research reports and other analytical pieces about different aspects of roads (captured in the diagram below). Some of these include organisations which do not produce official statistics (and who might be interested in voluntary compliance), which reinforces the idea that families are not just about official statistics but about numerical information on a particular topic.

How do families fit with the refreshed Code?

The draft Code of Practice for Statistics, about which we are currently consulting, is structured around three pillars – Trustworthiness, Quality and Value. Among the principles that support Value are that statistics should be insightful – helping to clearly answer society’s important questions – and that statistical production should be innovative – so that the statistics remain relevant in a changing world.

The idea of families of statistics plays right into this. In terms of insight, approaching the production and presentation of statistics through the strategic lens of a family helps to enable a complete picture of the statistical topic to be provided, and encourages producers of statistics to work collaboratively with producers of related statistics and topic experts (Principle V2, practice 3, draft Code of Practice for Statistics ). And it supports the explanation of the coherence of the statistics with other related data sources and statistics, and signposting to the related statistics (Principle V2, practice 4, draft Code of Practice for Statistics ). In terms of innovation, the family approach helps producers to seek out new partnerships which could improve the value of their statistics (Principle V4, practice 1, draft Code of Practice for Statistics) and to explore the potential of new and existing data sources (Principle V4, practice 2(i), draft Code of Practice for Statistics).

What will OSR do about families?

For us, the family approach will support the way we are increasingly looking at issues systemically: reviewing and reporting on issues and opportunities that cut across the statistical system. As part of our increasing focus on themes, as described in our Business Plan, we will work with statistical Heads of Profession (HOPs) across government to support their development of families of statistics in the areas for which they are responsible, working with users of the statistics.

What should statistical producers do next?

I mentioned above that we will work with statistical HOPs across government to support their development of families of statistics. In preparation for this it would be really helpful if they could:

Start to think about how, in practical terms, families could benefit them and improve TQV in their outputs, and how they might start to use families in their statistical planning, and their production and dissemination work. This might be a helpful starting point for discussion:

trustworthy

leadership and coordination across the system, including in those cases where organisations’ responsibilities relate only to part of the statistical value chain, such as NHS Digital which specialises in ‘data’.

taking account of needs of wide range of decision-makers not just Government

orderly release

quality

fully exploiting administrative data from various sources

clarifying responsibility for fixing data problems

standards for management information

value

easier access to statistics e.g. for researchers

protecting insight – complement latest snapshot data

Consider how broadly to define families. What level of granularity is most appropriate?

Any questions?

If you have any questions about families of statistic or would like an accessible version of the diagrams, please contact me on regulation@statistics.gov.uk

More generally, the values of OSR include being: externally engaged and connected; enquiring and open-minded; and inclusive and listening to others – we want to listen and learn. So, if this blog stimulates any other thoughts, please let me know.