Announcement of changes to GDP(O) improvement programme

Marilyn Thomas, Office for National Statistics

This announcement outlines changes that have been agreed to our GDP(O) improvement programme. The changes have been agreed with the UK Statistics Authority, and have been made in order to align the improvement programme more closely with our Economic Statistics Transformation Programme (ESTP). In short, the programme of GDP(O) industry reviews has been superseded by a more holistic approach to improvements across national accounts as a whole. The new approach will focus on comparative analysis of the monthly and annual approaches to the measurement of the output measure of gross domestic product (GDP), to inform the development of the new national accounts target operating model, including the introduction of quarterly supply use balancing. Additionally, we remain committed to reviewing and providing more detail on the wide range of administrative data sources used in the production of the short-term output indicators, in line with the Authority's Regulatory Standard for the Quality Assurance of Administrative Data.

In the UK, the output approach to measuring gross domestic product (GDP(O)) is based on a comprehensive and wide-ranging suite of short-term output indicators that are used to compile the Index of Services, Index of Production, Retail Sales Index and Output in the Construction Industry. As part of our commitment to continuous improvement, a number of quality improvement programmes have been implemented. For example, a programme of industry reviews was conducted between December 2012 and September 2016 to review the concepts, methods and data sources underpinning the short-term output indicators to ensure that they remained fit for purpose. It also demonstrated our commitment to quality assure outputs as part of the Code of Practice for Official Statistics. This programme of industry reviews mirrored similar work conducted between 2002 and 2009 during which time the Index of Services achieved National Statistics status in April 2007, due at least in part to the existence and impact of the industry review programme.

The commencement of the Economic Statistics Transformation Programme (ESTP) in 2016 provided an opportunity to reassess the GDP(O) improvement programme, in terms of its value with regard to the improvements delivered to GDP(O), and more widely to national accounts as a whole. As a result of the reassessment, it was recognised that, while the industry review programme delivered improvements to the output measure of GDP, an expansion of the improvement work to provide a more holistic focus across national accounts could deliver greater improvements. Therefore, a proposal for change to the improvement strategy was discussed with the UK Statistics Authority in September 2016. The outcome is that the programme of industry reviews has been superseded by 2 improvement work-streams, which are now under way: ESTP analysis work; and Quality Assurance of Administrative Data (QAAD).

As we move towards delivering our strategic vision for the future of national accounts a variety of source confrontation is required. A comparative analysis of the monthly and annual approaches to the measurement of the output measure of GDP will be undertaken, to inform the development of the new national accounts target operating model, including the introduction of quarterly supply use balancing. An update on the progress and outcome of this work will be provided in due course.

In 2015, the UK Statistics Authority published a Regulatory Standard for the Quality Assurance of Administrative Data (QAAD). This QAAD Regulatory Standard is used to assess statistics derived from administrative sources against the Code of Practice for Official Statistics. It is published alongside the Administrative Data Quality Assurance Toolkit, which is the mechanism that the Authority uses to determine compliance.

The standard encourages risk-based judgement and supports a proportionate approach, recognising that not all administrative data sources are high risk. As a result, the standard is pragmatic, and the toolkit that supports it provides helpful guidance to statistical producers about the practices they can adopt to assure the quality of the data they receive. A risk and profile matrix (Table 1) is used to evaluate the likelihood of quality issues arising in the data that may affect the quality of the statistics, and to assess the nature of the public interest served by the statistics.

The toolkit is built around the quality assurance (QA) matrix which presents the levels of assurance for 4 areas of practice:

• operational context and administrative data collection

• communication with data supply partners

• QA principles, standards and checks applied by data suppliers

• producer’s QA investigations and documentation

The QAAD reviews are conducted broadly at divisional level of the UK Standard Industrial Classification 2007 (UK SIC 2007), and are due to be completed by the end of 2018.