Accuracy and reliability

Overall accuracy

The statistics are subject to considerable sampling errors, particularly in subgroups and in the international transport.

Furthermore, missing data is around 6-8 percent of responses as a result of sold/deregistered vehicles and non-respondents.

There may be missing data which is not recognizable in the form of falsely reported stands stills when the vehicle is incorrectly reported to have stood still in the surveyed week in spite of the contrary. This will lead to underestimation of the true extent of transport.

Sampling error

According to the EC regulation the statistical results on the main variables weight of goods, kilometres driven with load and transport performance (tonnes-km) for both total transport and national transport must be within a coefficient of 5 percent. At quarterly level the Danish statistics does not meet the requirements.

The uncertainty is greatest in the international transport for which no target value is set.

Non-sampling error

The frame population includes all road goods vehicles above 6 tonnes total laden weight regardless of use, while the target population is road goods vehicles carrying freight. Around 7 percent of the frame population does not carry freight.

The statistics are sensitive to incorrectly reported stand still. Currently there are no alternative sources for the validation of this type of errors. Approximately 20-25 percent of the vehicles in the sample is reported as being inactive in the reference week. Since the weight on average is about 235 (13 * 36,000 / 2,000), the incorrect reporting could lead to considerable underestimation.

Missing reports are formally modest in cases of sold/deregistered vehicles and non-response. In reality, there may be an unknown underreporting hidden in the categories stand still and no available driver.

By treating sold/deregistered vehicles as non-response, it is assumed that there is no separate information in the information that the vehicle is sold, but that the transport of the vehicle can be represented by the vehicles which have responded.

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

There is considerable uncertainty associated with the statistics.

In particular, in some subgroups and in the international transport statistics there is great uncertainty in the figures. On some key variables in the international transport the confidence interval is between 15 and 25 percent. The national transport is considerably more precise.

Missing data constitutes 6-8 percent of reporting and is partly due to vehicles sold or deregistered between the sampling and the data collection and partly non-response. The latter is around 1 percent in the preliminary figures and less than 0.1 percent in final figures. Adjustments take this into consideration.

Besides the registered missing data, there may also be an underestimation of the results as a result of falsely reported stands stills when the vehicle is incorrectly reported to have stood still in the surveyed week. This type of non-response is difficult to identify due to lack of proper comparable data.

The statistics are not revised significantly over time.

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

Quarterly statistics are preliminary and revised regular. Final figures is published in connection to the annual figures typically around three and a half months after the end of the reference year.

The reason for revisions are mostly caused by late replies from data providers.

If significant errors comes to the knowledge of Statistics Denmark an extraordinary revision will be done. Registered user of the online databank, http://www.Statbank.dk will be notified in case of such extraordinary revisions.