Accuracy and reliability

Overall accuracy

The accuracy of the estimation of Household final consumption expenditure (HFCE) depends on the quality and coverage of the underlying data sources.

The main sources used for the distribution of HFCE by consumption groups (COICOP18) are the Household Budget Survey (HBS), retail trade statistics, and VAT data. The HBS is associated with considerable sampling uncertainty, as it covers a relatively limited number of households and therefore requires grossing up to the full population. In addition, there is a risk of underreporting certain types of expenditures, particularly cash purchases and frequently purchased goods, which may lead to biases in the consumption structure.

Certain consumption components, such as undeclared work and imputed rent for owner-occupied dwellings, are based on estimates and assumptions, which further reduces the accuracy of these areas.

To ensure consistency between the level of total household consumption and the rest of the national accounts, VAT totals are used as a benchmark for the overall level of consumption, and developments in the household consumption are assessed against VAT revenue and other indicators of private demand.

In the annual national accounts, HFCE is derived within the Supply and Use Tables (SUT) balancing framework, ensuring consistency between supply and demand through full integration in the national accounts system. Within this framework, HFCE is adjusted as part of the overall balancing process, reflecting the relatively higher uncertainty of certain input data sources, in particular HBS compared to more robust structural statistics.

In the quarterly national accounts, HFCE is estimated using short-term indicators and model-based approaches, as full SUT balancing with products is not applied at this stage. Quarterly estimates are subsequently benchmarked to the annual accounts, where HFCE is integrated into the SUT balancing framework.

Uncertainty is highest in the earliest versions of the national accounts, where detailed source data are not yet available. At this stage, estimates are based on short-term statistics and retail trade indicators, and the COICOP distribution is extrapolated from the latest final year. As new and more detailed sources become available, they are incorporated progressively, reducing uncertainty in both levels and distribution.

Revisions are an integral part of the compilation process. As additional source data become available and methodological improvements are introduced, HFCE is revised accordingly. This includes routine revisions between early and final annual estimates as well as major benchmark revisions, where the full time series is re-estimated within a consistent SUT framework. As HFCE is derived within the national accounts balancing system, it remains indirectly determined and therefore sensitive to revisions in other components of supply and use.

Sampling error

Not relevant.

Non-sampling error

Non-sampling errors in Household final consumption expenditure (HFCE) arise mainly from coverage, measurement, and classification issues in the underlying data sources, as well as from estimation procedures used in the compilation process. Many of the data sources used in the HFCE are not fully comprehensive. As a result, adjustments are made to achieve full coverage of household consumption expenditure. This includes assumptions for areas where direct data are limited, such as fringe benefits and parts of the informal economy, where underreporting may occur.

Classification issues in HFCE mainly arise when integrating different data sources (e.g. VAT, retail trade statistics and administrative data) into a consistent COICOP-based national accounts framework, as well as aligning source data with national accounts concepts. The Household Budget Survey is collected according to COICOP, but minor inconsistencies may occur when the data are used in the national accounts due to harmonization of different data sources.

Additional non-sampling errors arise from estimation methods, including the use of indirect indicators, extrapolation of COICOP distributions from previous periods, and balancing adjustments to align different data sources.

Quality management

Statistics Denmark follows the recommendations on organisation and management of quality given in the Code of Practice for European Statistics (CoP) and the implementation guidelines given in the Quality Assurance Framework of the European Statistical System (QAF). A Working Group on Quality and a central quality assurance function have been established to continuously carry through control of products and processes.

Quality assurance

Statistics Denmark follows the principles in the Code of Practice for European Statistics (CoP) and uses the Quality Assurance Framework of the European Statistical System (QAF) for the implementation of the principles. This involves continuous decentralized and central control of products and processes based on documentation following international standards. The central quality assurance function reports to the Working Group on Quality. Reports include suggestions for improvement that are assessed, decided and subsequently implemented.

Quality assessment

The ESA 2010 regulation requires that Eurostat assess the quality of data reported under the ESA transmission program. This is done on the basis of the countries' quality reports which are not published independently by Eurostat. The report is prepared annually. Read the quality assessment of Denmark's national accounts in Quality Report, Denmark 2020 - National Accounts.

The quality assessment is based on standard quality criteria defined in the European Statistical System, including relevance, accuracy and reliability, timeliness and punctuality, coherence and comparability, and accessibility and clarity. Quality is measured and monitored through regular validation and consistency checks, revision analysis and confrontation of data across related national accounts domains.

Information on quality management, revision practices and methodological documentation is publicly available on [Statistics Denmark’s] website, while the detailed country quality reports used by Eurostat are not published separately.

Data revision - policy

Statistics Denmark revises published figures in accordance with the Revision Policy for Statistics Denmark. The common procedures and principles of the Revision Policy are for some statistics supplemented by a specific revision practice.

Data revision practice

Household final consumption expenditure is revised according to the same principles as the national accounts as a whole. Ongoing revisions may occur when new or updated sources become available. In the quarterly and annual accounts, changes from the sources are incorporated as more complete data become available, which may lead to minor adjustments of previously published figures.

Indirect revisions may also occur when changes in the sources affect the accounting of the economy’s total supply and use, for example in the financial statements. Such changes can impact the overall product balances and, consequently, the functional distribution, including household consumption.

Comprehensive revisions are carried out as part of the national accounts’ five-year revision cycle. During these revisions, longer time series for household consumption are updated to ensure consistency with the other components of the national accounts and to incorporate any changes in methodology, classifications, or source coverage. Larger revisions may also occur in connection with the implementation of new international standards, such as ESA, where the entire time series back to 1966 is re-estimated