People want to make timely decisions and need data and statistics to inform their decision-making. However, analysts must balance the need for more timely data against the need for accurate, coherent and comparable data.
The need for as close to real-time as possible data has been a hallmark of the past year. The pandemic has led to a demand for very timely data to ensure any decisions, for example about lockdown restrictions or relaxations, are based on the most up-to-date evidence. The response of the statistical system has been impressive. New data sets have been brought online to meet this need and existing data sets have been used and shared in new ways to enable this to happen. Examples include the Transport use during the pandemic statistics mentioned previously (case study 2), the Department for Education’s data on attendance in education and early years settings during the coronavirus (COVID-19) outbreak, and the experimental data provided in Economic activity and social change in the UK, real-time indicators.
Case Study 3: Economic activity and social change in the UK, real-time indicators
The ONS published the first of its weekly Economic activity and social change in the UK, real-time indicators (previously called Coronavirus and the latest indicators for the UK economy and society) publications in April 2020, one month after the UK first went into lockdown and has continued to do so ever since. The publication contains a series of economic and social indicators (for example, card spend, road traffic and footfall), which come from a variety of different data sources. These assist policymakers with understanding the impact of the pandemic and gauging the level of overall economic activity.
As outlined to users, the statistics are considered as experimental indicators in line with OSR’s COVID-19 guidance for statistical producers. These new indicators reflect the trade-off between their prompt availability versus the corresponding impact on accuracy, a balance that users told us they appreciated to ensure they had readily available information for decision-making.
However, timely data can be associated with more uncertainty and less accuracy and can potentially be misleading. The need for more timely data must therefore be balanced against the need for accurate, coherent and comparable data timeliness, and in the context of user need. For example, if the link between COVID-19 infections, hospitalisations and deaths stabilises, we may only need to understand the infections data on a near real-time bases and get a strong indication of the other rates from this. And, as with all data and statistics, communicating any uncertainty and the limitations of data is crucial. In our Rapid Review of Coronavirus, the UK economy and society, faster indicators we noted the value added to decision-makers and society of these more timely economic statistics, particularly in the context of the pandemic. We also noted the importance of the methodological information to help explain any potential bias, strengths and limitations which arise from the use of these more timely and innovative data sets. There is value in early indicators which are more timely, but understanding their limitations and the value of a final, high quality statistical time series is important too.
Looking to the future
The UK statistical system should maintain this innovative and impressive approach to more timely data and statistics. These new, more timely statistics should continue to be improved upon and developed to improve their trustworthiness, quality and value. Over the coming year, we will also be carrying out an Insight project on how producers describe uncertainty in the statistics they publish. The statistical system is never standing still, and it will need to continue to evolve as it has over the past year.Back to top