Accuracy and reliability
Contact info
External Economy, International Trade in Service.Selma Mustafic Mulalic
+45 23 69 46 64
Get as PDF
In the first release of the figures for foreign trade in services there will be a certain degree of uncertainty as a minor part of the data has either not been reported yet or has errors to a degree that it cannot be included in the release. In these cases data will be supplemented by estimations. The reliability of the figures for a given quarter increases in later releases. The final figures are to be considered as fairly reliable, to a decreasing degree though the more detailed level that is applied.
Overall accuracy
The statistics on foreign trade in services are basically compiled on partly a cut-off sample of Denmark’s 390 largest firms engaged in this trade (monthly reports) and partly a stratified sample of about 1.300 small and medium-sized firms (annual reports). So the Survey on international trade in services is a sample based survey and data is grossed up to the total population. This entails by its very nature some inaccuracy, especially regarding the geographical dimension. An important element of inaccuracy is attached to the frame from which the sample is drawn. The frame was first derived from the settlement statistics of Danmarks Nationalbank, which is abolished in 2004. Effective from 2009 a new frame has been taken into use. This frame has been delimited from Business register and special “screening” surveys conducted every fifth year, last time in 2013, where 5.000-6.000 firms have been questioned.
Finally it must be considered that the concepts being employed in the statistics are rather complicated. Accordingly misunderstandings in the reports leading to inaccurate compilations are unavoidable. This problem is constantly addressed by contacting the reporters when suspicions of misunderstandings are raised. Special analyses have been conducted on the items sea transport, travel, insurance, merchanting, government services (n.i.e.), construction services, and services between affiliated enterprises (n.i.e.) and most lately on intellectual property services. The travel item entails some difficulty, especially travel debits. It is compiled using different information on consumption by Danes abroad, number of nights abroad, and transport abroad from statistics from other countries; but the risk of error is fairly big, particularly concerning small partner countries. This error margin can, however not be calculated.
Sampling error
The statistics on foreign trade in services are mainly based on a sample survey, which entails sampling error. The sampling error is especially high for the most detailed levels.
The coefficient of variation (CV) is used to quantify sampling error. The coefficient of variation is the ratio of the standard error to the estimate i.e. the relative standard error. The estimated coefficients of variation for survey on foreign trade in services (provisional figures): Export of services (total): app. 0,5 pct. Import of services (total): app. 0,7 pct. With a usual confidence interval of 95 pct. this means that the relative sampling error is at most 1 pct. for exports and 1.4 pct. for imports. For example, if the export is estimated at 200.000.000, the sampling error is app. 1 pct. i.e. app. 2.000.000.
The estimated coefficients of variation for the more detailed levels can be substantially higher (see attached document here). Values with CVs greater than 35 are suppressed.
Non-sampling error
An important element of inaccuracy is attached to the frame from which the sample is drawn. The frame was first derived from the settlement statistics of Danmarks Nationalbank, which is abolished in 2004. Effective from 2009 a new frame has been taken into use. This frame has been delimited from Business register and special “screening” surveys conducted every fifth year, last time in 2013, where 5.000-6.000 firms have been questioned.
Finally it must be considered that the concepts being employed in the statistics are rather complicated. Accordingly misunderstandings in the reports leading to inaccurate compilations are unavoidable. This problem is constantly addressed by contacting the reporters when suspicions of misunderstandings are raised. Special analyses have been conducted on the items sea transport, travel, insurance, merchanting, government services (n.i.e.), construction services, and services between affiliated enterprises (n.i.e.) and most lately on intellectual property services.
The travel item entails some difficulty, especially travel debits. It is compiled using different information on consumption by Danes abroad, number of nights abroad, and transport abroad from statistics from other countries; but the risk of error is fairly big, particularly concerning small partner countries. This error margin can, however not be calculated.
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
Compared to statistics in countries, which are comparable with respect to size and development, the Danish statistics on foreign trade in services are considered to be of good quality. Some reservation, however, has to be indicated with respect to the distribution on partner countries.
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
After the first publication of the international trade in services it is continuously adjusted, as supplementary or adjusted statistical material appears. The supplementary information implies that the final calculation of the international trade in services is only prepared about 2-3 years after the expiry of the reference year. According to practice the data of the months of the previous year are locked by late September. Simultaneously the data of the preceding year are revised and locked again. The last revision is conducted according to the final National Accounts about 3 years after the expiry of the reference year.