How Statistics Can Help — Going Beyond COVID-19
By Walter J. Radermacher (Sapienza University of Rome & the Federation of European National Statistical Societies)
1. “Statistics — A matter of trust” reloaded
It is rightly pointed out that in the midst of a crisis of enormous dimensions we needed high quality statistics with utmost urgency, but that instead we are in danger of drowning in an ocean of data and information [1]. The pandemic is accompanied and exacerbated by an infodemic [2]. At this moment, and in this confusion and search for solutions, it seems appropriate to take advice from previous initiatives and draw lessons for the current situation. More than 20 years ago in the United Kingdom, the report “Statistics — A Matter of Trust” [3] laid the foundations for overcoming the previously spreading crisis of confidence through a solidly structured statistical system. This report does not stand alone in international comparison. Rather, it is one of a series of global, European and national measures and agreements which, since the fall of the Berlin Wall in 1989, have strengthened official statistics as the backbone of policy in democratic societies, with the UN Fundamental Statistical Principles [4] and the EU Statistics Code of Practice [5] being prominent representatives. So, if we want to deal with our current difficulties, we should address precisely those points that have emerged as determining factors for the quality of statistics, with the following three questions: What (statistical products, quality profile)? How (methods)? Who (institutions)? The aim must be to ensure that statistical information is suitable for facilitating the resolution of conflicts by eliminating the need to argue about the facts and only about the conclusions to be drawn from them.
In the past, this task would have led relatively quickly to a situation where the need for information would have been directed to official statistics as the preferred provider; this has changed recently for many reasons. On the one hand, there is the danger that the much-cited data revolution and learning algorithms (so-called AI) are presented as an alternative to official statistics (which are perceived as too slow, too inflexible and too expensive), instead of emphasizing possible commonalities and cross-fertilization possibilities. On the other hand, after decades of austerity policies, official statistics are in a similarly defensive situation to that of the public health system in many respects and in many countries: There is a lack of financial reserves, personnel and know-how for the new and innovative work now so urgently needed.
It is therefore required, as in the 1990s, to ask the fundamental question again, namely, do we (still and again) really deserve official statistics as the backbone of democratic decision-making, and if so, what should their tasks be, how should they be financed and anchored in the political system? To do this successfully, it is necessary to approach the field of interactions between the world of data, facts, information, indicators, etc. on the one hand, and the world of opinion-forming, decision-making, media, etc. on the other, with a somewhat more precise and differentiated view [6]. It is important to understand how statistics and society are co-constructed and co-produced, including in particular “governance by the numbers” and “informational governance” [7].
2. Which Crisis?
Given the urgency and stress of the current situation, it seems natural to focus the statistical issues of Corona on the decisions that are about to be taken. At this point, however, a broader perspective and longer horizon is advocated [8]. Why does a more strategic and long-term view seem so essential right now, when we hardly have time for the most dramatic questions?
There are two important arguments for this:
Firstly, the most pressing risks identified by the World Economic Forum in January 2020 [9] have not simply disappeared because we are now fighting a pandemic: “Failure of climate-change mitigation and adaptation, extreme weather events, natural disasters, water crises, biodiversity loss and ecosystem collapse, cyber-attacks etc.” The question is therefore to what extent it is possible to design the measures for exits from COVID in such a way that they do not take us back to a supposed normality ex ante, thereby missing the opportunity to make this normality more compatible with the global strategy of sustainable development [10]. This is of course not a statistical debate but a scientific [11] or political [12] one.
Secondly, it must be borne in mind that more substantial changes, extensions or accelerations of official statistics cannot be realised overnight. Official statistics are a kind of ocean liner whose course can only be changed with considerable advance planning and preparation. It is therefore time to look far ahead now in order to be able to adapt to the information needs of the future, two to five years from now.
3. Which Statistics?
Let us approach the question of the future of official statistics in such a way that we unfold the trinity of statistical quality and start with the statistical programme, i.e. the
What: The traditional domains of economic and social statistics will be consulted, but in a way which will call into question their division into specialised domains. This is illustrated by the example of agricultural statistics. Whereas in the past the aim was to quantify farmers’ production performance as quickly and accurately as possible, the aim will be to be able to cast statistical light on sustainable food production from the cradle to the grave, including agricultural production in connection with its inputs, outputs as well as its impact on biodiversity, water protection, etc., and international trade in agricultural goods. Let us approach the COVID exit with a second example, by asking ourselves what effects the financial support measures have not only on public finances, unemployment or inflation, but also on the conformity of industrial production and consumption with the goals of climate protection. In addition, however, it will also have to deal with areas which do not yet belong to the programme of official statistics or which will be given higher priority in it. Current examples of this are migration (development especially since 2015), health (current pandemic) and biodiversity (highly classified as a risk), for which new statistics or statistics with improved quality (speed, level of detail, representativeness, etc.) are clearly needed [13].
How: The needs for the reform of statistical production processes are very clearly summarised in the Bucharest Memorandum of European Statistics of 2018 [14], which among other things states “the variety of new data sources, computational paradigms and tools will require amendments to the statistical business architecture, processes, production models, IT infrastructures, methodological and quality frameworks, and the corresponding governance structures.” In addition, it will also be a matter of official statistics increasingly acting not only as a producer of information but also as a service provider. Such services should generally have to do with available competencies, strengths and experience: One could generally help manage the quality of statistics, even if they are produced outside the factory walls of official statistics. For example, statisticians could be helpful in the design of measurement concepts (especially surveys, such as a “stratified random sampling of biodiversity across space and taxa” [15]) as well as in the use of imputation and estimation methods or in the application of national accounting to other subject matters (e.g. by calculating ‘Trade in Value Added [16]’ or improving ‘Ecological Footprint Indicators [17]’). They could assist in improving communication and providing information. They could take over the role of a standard setter and certifier of statistical standards.
Who: The institutions of official statistics are involved in the public administration of their country (of the supranational or international level, respectively). They enjoy a status of professional independence that is more or less guaranteed by the respective state governance. What is much more important, first of all, is the commitment of official statistics to the basic principles of good public administration in terms of e.g. citizen participation, accountability, etc. What is important in the near future, therefore, is to emphasise these strengths of a public institution through which trust can be strengthened and maintained. At the same time, networking with the scientific community and partnerships with other producers of statistics is to be further intensified, open data access is to be created for everyone and, at the same time, the confidentiality of individual data is to be safeguarded. Finally, there is an urgent need to invest more in the general education of understanding, skills and abilities to handle facts, graphics and maps. Only if the population (and of course the political scene in particular) is sufficiently aware of the differences in the quality of statistical information, if one is capable of distinguishing between fake and fact, then a basis of trust can grow and flourish.
4. Which Policy?
If there is data for policy, there is also a policy for data (and statistics). In principle, policymakers must be expected to act quickly now and create the conditions for the statistical infrastructure to develop as described above in the coming months and years. It is essentially a matter of giving the status of generating evidence relevant to decision-making in the public sector the status that this has long since been given in the private sector. The staffs and teams for current and future crises treatment will be composed of experts from a wide range of disciplines; statisticians must not be (further) missing in this context. Statistics are essential if the infodemia and proliferation of data described above is to be avoided. The creation of trust, efficiency and effectiveness in the public information sector will only succeed with official statistics as a powerful actor. However, in order for official statistics to be able to cope successfully with such a rapid and radical development of its role, the appropriate conditions must be created in terms of governance, finances, personnel, etc.
5. Conclusion
Hardly ever has the lack of adequate statistics for making essential political decisions and gaining the support of the general population for their consequences been as visible and painful as it is now, during the pandemic crisis. Seldom has so much public money been invested by governments to combat the health, social and economic consequences of a crisis. The question is whether these monumental financial support programmes are used to link a direction or a mission to them, whether the investments are used for innovation in the sense and for the goals of “entrepreneurial states” [18]. However, it would be fatal if at least a small fraction of this money was not used to fill the obvious gaps in the public information infrastructure.
Dr. Walter J. Radermacher was Director General of Eurostat and Chief Statistician of the European Union from 2008 to 2016. He worked at Destatis, the German Federal Statistical Office, for 30 years, ultimately as its President and Federal Returning Officer. He was the first Chair of the UN Committee of Experts on Environmental-Economic Accounting (UNCEEA) from 2005 to 2008. Since 2017 he has been a Researcher at the Department of Statistical Sciences, Sapienza University of Rome, and the President of FENStatS, the Federation of European National Statistical Societies.
References
[1] https://medium.com/data-policy/mapping-how-data-can-help-address-covid19-a7be2e631aec
[2] https://www.un.org/en/un-coronavirus-communications-team/un-tackling-%E2%80%98infodemic%E2%80%99-misinformation-and-cybercrime-covid-19, https://www.youtube.com/watch?v=jgmdEk7rTxU
[3] https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/260823/report.pdf
[4] https://unstats.un.org/unsd/dnss/gp/fundprinciples.aspx
[5] https://ec.europa.eu/eurostat/web/quality/european-statistics-code-of-practice
[6] See W. Radermacher, Official statistics 4.0 — Verified Facts for People in the 21st Century, https://link.springer.com/book/10.1007%2F978-3-030-31492-7
[7] https://officialstatistics.com/news-blog/why-should-there-still-be-need-elaborate-official-statistics-future
[8] See also the discussion platform in https://officialstatistics.com/news-blog/crises-politics-and-statistics
[9] http://www3.weforum.org/docs/WEF_Global_Risks_Report_2019.pdf
[10] https://sustainabledevelopment.un.org/?menu=1300
[11] https://www.theguardian.com/books/2020/may/07/we-are-living-through-the-first-economic-crisis-of-the-anthropocene
[12] See for example https://www.politico.eu/article/bailout-europes-chance-to-go-green-is-in-danger/
[13] For the short-term mapping of information needs see https://medium.com/data-policy/mapping-how-data-can-help-address-covid19-a7be2e631aec
[14]https://ec.europa.eu/eurostat/documents/7330775/7339482/The+Bucharest+Memorandum+on+Trusted+Smart+Statistics+FINAL.pdf/59a1a348-a97c-4803-be45-6140af08e4d7
[15] M. Dornelas, G.N. Daskalova, Nuanced changes in insect abundance, Science Magazine Vol 368, 6489, 24. April 2020, p 368–369
[16] http://www.oecd.org/industry/ind/measuring-trade-in-value-added.htm
[17] https://www.footprintnetwork.org/our-work/ecological-footprint/
[18] https://www.weforum.org/agenda/2020/04/coronavirus-covid19-business-economics-society-economics-change/
This is the blog for Data & Policy (cambridge.org/dap), a peer-reviewed open access journal exploring the interface of data science and governance. Read on for five ways to contribute to Data & Policy.
