Accuracy and reliability

Overall accuracy

The statistics are based on the coordination of different statistical registers using a unique person identification. This process is considered to be very accurate. The effect of uncertainty is estimated to be small and people with missing income or educational background classed as uninformed. Sincethe statistic is based on a total count of participants, the summers by age and gender will be adequate. There are no duplicate participants in the statistics, but a person may appear several times in the statistics if they have participated in several courses.

Courses and Adult Education - Folk High Schools is a total count pf participants based on information reported by the schools. The primary sources of uncertainty are errors in the reports of the schools, as well as any folk high schools such as Statistics Denmark are not aware of. The overall precision is estimated to be high.

The Population general quality and reliable ratings at much high. The register may be affected by a lack of reports of immigration and emigration, but this is not considered to be a problem in relation to these statistics.

The precision and reliability of the Highest Education Attained varies depending on the source of information coming from. Just over 80 per cent. Information comes from administrative sources, such as the educational systems of the educational institutions, which are considered to be reliable. Other sources will often be less reliable, such as studies on immigrants' education. For these statistics, the accuracy of educational information for students with immigrant or descendant status would therefore be less god.

The quality is generally assessed by being much higher for data from the Income Statistics for all the income types covered by the statistics. The main source of data is SKAT, where most of the information has been basically validated. Elements such as lottery winnings and black earnings are not covered by the statistics. The accuracy in relation to these statistics is considered to be high.

Sampling error

Not relevant for this statistic.

Non-sampling error

The statistics are based on the interconnection of different statistical registers, and sources of uncertainty in the individual registers will influence the results in these statistics.

All registered and active schools have reported. Every year, between zero and five schools are about to be closed down, set up or for other reasons do not have participants who have not reported. Lapses may occur as a result of non-valid data in the reports, which cannot be corrected despite contacting the data provider. The extent of this is limited. In case of lack of background information regarding education and income are categorized as uninformed in the tables. However, the participants will be included in all sums, and divided by gender and age.

More than 80 per cent. of the information for the highest education completed by the population comes from administrative sources, such as the educational systems of the educational institutions. Other sources are not so closely linked to educational institutions and will often be less reliable. These are used only if no other information is available and may be self-reported or imputed. For groups of persons where the information is largely not from administrative sources (eg immigrants), the uncertainty is greater than the uncertainty for the other population.

Income data on which these statistics are based are deducted in August after the end of the year. As the tax returns are not regularly audited, this means that changes after that date are not included in the statistics. This primarily affects the self-employed, where a small part of the group is not finished at the time of withdrawal. It is considered to have no effect on the results of this statistic.

For income information, the proportion of uninformed 3-6 per cent. for the short courses, and 21-25 per cent. for the medium and long courses. For educational information, the proportion of uninformed is 5-7 per cent. for the short courses and 23-30 per cent. for the medium and long courses. The difference in the proportions of uninformed is primarily due to the proportion of participants with foreign background. In the description of the background for the middle and long-term participants - it is based on their families' education and income. Since the registered amount of foreigners are higher, the proportion of uninformed will also be higher. In relation to provenance and residence deducted from the Population Register, the share of uninformed is 7-10 per cent. for the common number of participants. Not all uninformed are basic in missing register information. A smaller proportion of the uninformed is due to sensitive personal data placed in the uninformed category due to discretion of the tables.

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 reliability of the statistics is considered to be good, as it is based on validated data from registers that are used for other official statistics. Error records or missing updates to the administrative registry are the main sources of uncertainty.

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

There may be revisions to the data through corrections in the individual source registers.