Accuracy and reliability

Overall accuracy

The accuracy of the level of detail at which data are published is assessed to be good for the public sector. However, the earliest years, the statistical system and data quality have been improved.

In the private sector the data on absence is calculated on basis of a sample of enterprises of ten or more employees. Especially during the first years we do not expect to receive data on absence from a great number of enterprises. A lot of enterprises have not established a system for registering the periods of absence in time and several have not registered the data correctly. Furthermore registering the data is time-consuming and not necessarily a task of interest for the enterprise itself. Consequently the registration of the periods of absence is not always complete. The first data for the private sector referred to 2006 but due to poor quality the previously published data for 2006 was removed from Statbank Denmark.

Periods of maternity leave in the central government sector are based on data from the register of benefits during sickness or in connection with childbirth, as a great number of the respondents have not reported any periods of maternity leave. Periods created on the basis of payment of benefits are longer but not as numerous. consequently, comparisons between sectors should only be made with caution.

Due to the reform of municipalities in 2007 the connection between the absence period and the corresponding job has caused great problems in 2006, 2007 and 2008. Consequently, comparisons between years should only be made with caution.

Change of systems to register absence data might cause problems with the quality of the reported periods of absence and consequently the results of the units concerned might be uncertain. This has been the case for parts of the local government sector from 2010 and forward.

Sampling error

The surveys of the governmental and local government sector are supposed to be universal which means that all employees are in principle included. Consequently there is no sampling error.

The private sector is based on a representative sample of about 2600 enterprises. The total absence rate for own sickness is determined with a 95 percent confidence interval to vary around +/- 0.05 percent. Sampling errors for divisions on e.g. gender or industry are considerably higher.

Non-sampling error

The results of the Statistics of Absence are especially dependent on the fact that both absence and wages are reported for all employees in the enterprises, governmental and municipal institutions etc. Especially concerning the Statistics of Absence it is difficult to establish whether absence is reported for all employees. In order to calculate the different measures of absence the absence periods are matched with the belonging job from the statistics of earnings. It is important that the information on the persons are reported to both statistics and that the identification variables are the same in both statistics.

In cases where the actual hours of absence are not reported people are assumed to work 5 days a week and to be absent the whole day. The hours of absence are calculated on basis on the degree of employment from the Statistics of earnings. The actual hours of absence are not reported for the governmental sector when it comes to periods that last a whole day. Up till 2017 hours of absence are not reported for certain municipalities and regions and for the private sector this is the case for defective periods of absence.

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 accuracy of the level of detail at which data are published is assessed to be good for the public sector. However, the earliest years, the statistical system and data quality have been improved.

In the private sector the data on absence is calculated on basis of a sample of enterprises. Especially during the first years we do not expect to receive data on absence from a great number of enterprises. A lot of enterprises have not established a system for registering the periods of absence in time and several have not registered the data correctly. Furthermore registering the data is time-consuming and not necessarily a task of interest for the enterprise itself. Consequently the registration of the periods of absence is not always complete. The first data for the private sector referred to 2006 but due to poor quality the previously published data for 2006 was removed from the Statbank Denmark.

Periods of maternity leave in the central government sector are based on data from the register of benefits during sickness or in connection with childbirth, as a great number of the respondents have not reported any periods of maternity leave. Periods created on the basis of payment of benefits are longer but not as numerous. consequently, comparisons between sectors should only be made with caution.

Due to the reform of municipalities in 2007 the connection between the absence period and the corresponding job has caused great problems in 2006, 2007 and 2008. Consequently, comparisons between years should only be made with caution.

Change of systems to register absence data might cause problems with the quality of the reported periods of absence and consequently the results of the units concerned might be uncertain. This has been the case for parts of the local government sector from 2010 and forward.

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.