Accuracy and reliability
Contact info
Business Dynamics, Business StatisticsMahtab Keshavarz
+45 39 17 31 15
Get as PDF
Approx 3,200 responses have been used in the grossing up procedure. The results are grossed up so that they correspond to full coverage of the surveyed industries and size groups. Each enterprise in the sample is assigned a weight such that it represents a certain number of enterprises in the population. The grossing up procedure is based on the number of enterprises, and the number of fulltime employees within employment groups. Regarding the enterprises the response rate is 95 per cent for the survey. Loss is due to bankruptcy, take over, etc. The high response rate indicates that results are reliable as the statistical variance indicates. Measures of inaccuracy for selected variables are available.
Overall accuracy
As the survey is based on a sample in the private sector, all estimates are subject to inaccuracy in form of random variation. In particular, estimates broken down by industry and size must be regarded only as normative. It must be emphasized that enterprises are asked to give a best estimate of ICT expenditure, which is due to the fact that ICT expenditure not always emerge from the financial statements of an enterprise. Sample inaccuracy for certain variables is calculated and indicated when results are published.
Sampling error
Confidence intervals (95%) for total expenditure and sub groups are:
- Total expenditure 57,6 ± 4,15 mia. kr.
- Hardware 6,4 ± 0,28 mia. kr.
- Other ICT equipment 2,8 ± 0,55 mia. kr.
- Standard software 9,9 ± 1,03 mia. kr.
- Special software 8,9 ± 2,84 mia. kr.
- ICT service 27 ± 2,35 mia. kr.
- Leasing 2,5 ± 0,17 mia. kr.
The variation will increase at detailed level of NACE and size groups of business.
Non-sampling error
In a few cases enterprises are organized with more than one business registration, in agreement with the enterprise, we ask the unit having the ICt-expenditures to respond to the questionnaire on behalf of all. In the survey the reporting unit will be regarded as one larger enterprise. Population of enterprises are selected according to ownership, activity (NACE code) and number of employee (more than 10 full time equivalent). The statistics covers almost 21 pct. of all FTE in the relevant NACE groups. The assumption is that under estimation in some units will be compensated by over estimation in other units. Non-response of 5,4 pct. Assumption there are no bias.
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
Sampling error has effect at detailed breakdown at general level statistics on ICT gives the right indication of expenditures.
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
Only final figures are published.