Accuracy and reliability

Overall accuracy

Some of the information in the accounting statistics is more detailed than the items required by the Danish Financial Statements Act. This applies, for example, to information on energy consumption. This can mean that enterprises may find it difficult to provide this information, and therefore data on this information is likely to be underestimated, as expenditure will instead be placed on other items such as external costs or consumption of goods, which will be overestimated.

Investment information is also not directly reflected in items in the accounts that comply with the Danish Financial Statements Act, but they can usually be deduced from a table in the notes to the accounts. One must therefore also expect a certain likelihood that the investments are experientially underestimated among the enterprises that fill and submit questionnaires to Statistics Denmark.

Accounting statistics are more uncertain at the workplace level than at the corporate level, as the distribution method is based on assumptions. For example, for combined enterprises, the method assumes that the individual workplaces have, as a starting point, accounting figures per year. man-years equivalent to the average for all uncombined enterprises in the same ownership and industry. However, despite the uncertainty, it is considered that the information is reliable at the main industry and regional level.

Sampling error

The main basis of the figures ( except number of enterprises, employees (in FTE) and persons employed (in FTE)) is questionnaire data collected for a sample of enterprises and information from TAX-authority. A sample can not give an accurate picture of the population , and therefore the figures are subject to some sampling errors.

For the calculation of confidence intervals the spread is used, which can be observed among the reported data. The spread is a measure of the variation in the data from individual firms, the larger the spread, the greater the variation. The calculation is performed to calculate the spread and thus confidence interval , taking into account the sample and the additional information from the TAX-authority. This special combination of a sample and additional information from the TAX-authority means that one can not use standard calculations and formulas when the spread is calculated. When you have information from two sources, it is not possible to calculate the spread exact - but only approximate. The method chosen to calculate approximate values ​​for the spread is to take samples in the sample ( Jackknife method). In industry and supply, revenue typically differs below +/- 1 billion. DKK as 95 per cent. confidence interval.

Non-sampling error

Population is defined by the industry in which the enterprises are registered in the Business Register. Inactive enterprises and enterprises with very limited activity are not included in the statistics. Uncertainty due to the non response is minimized by repeated twitching by incomplete reporting. For the financial year 2023, accounting data was received from 97 per cent. Of the enterprises that were withdrawn in the sample. Incorrect data reported and misunderstandings are minimized by checking the reported figures.

It is assumed that companies from which information has been received from the Danish Tax Authority (SKAT) or the Danish Business Authority and which belong to the same industry and have the same ownership form are comparable to companies in the sample. Therefore, missing entries in the tax accounts or annual accounts can be calculated based on the main entries, based on the companies that have reported in the sample.

The delimitation of genuinely active companies is based on model assumptions, which entail some uncertainty, especially in industries with low or uneven turnover. Since the criteria for including companies as active have changed over time, this may affect comparability. See "Comparability over time" for a more detailed description.

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 statistics provide a reliable picture of the economic situation of Danish businesses, as they are based on a broad sample, administrative data, and detailed accounts.

Some of the information in the accounting statistics is more detailed than the entries required by the Annual Accounts Act. This applies, for example, to information on costs for hiring labor. This may mean that companies may find it difficult to provide this information, and it is therefore likely that data regarding these details are underestimated. The expenses will instead be placed in other entries, such as external costs or consumption of goods, which will thus be overestimated.

Investment information is also not directly reflected in the entries in accounts that follow the Annual Accounts Act, but they can usually be derived from a table in the notes to the accounts. Therefore, one must also expect a certain likelihood that investments are underestimated among the companies that fill out and submit questionnaires to Statistics Denmark. Only from 2005 onwards are there data from the Danish Tax Authority (SKAT) on investment additions and disposals, so the reliability of investments is assumed to improve from this year.

The accounting statistics are more uncertain at the workplace level than at the company level, as the distribution method relies on assumptions. Despite the uncertainty, however, it is assessed that the information is reliable at the main industry and regional level.

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

For larger method shifts or detection of errors, the figures may be revised.