Accuracy and reliability
Contact info
Labour and Income, Social Statistics.Martin Faris Sawaed Nielsen
+45 23 69 90 67
Get as PDF
Data are based on a survey; hence there is some statistical uncertainty; especially on subgroups. In addition to sampling errors there might be a slight risk of bias. A calibration of the survey is carried out in order to limit any bias and make sure that the sample reflects the population on factors such as demographics and incomes. For the published variables the effect and risk of bias is assumed to be negligible due to the strong correlation with incomes.
Overall accuracy
As SILC is based on a sample of persons/household there are some statistical uncertainty related to the data. This is partly due to the presence of statistical uncertainty and partly due to the risk of biases. A calibration of the survey is carried out in order to limit any bias and make sure that the sample reflects the population on factors such as demographics and incomes. For the published variables on making ends meet, the burden of housing costs and economically vulnerable, the effect and risk of bias is assumed to be negligible due to the strong correlation with incomes.
The exclusion of persons not living in private households probably results in underestimation of social exclusion.
Sampling error
The following confidence intervals is calculated on the total sample in 2022. If smaller sub-populations for instance a specific age-group is selected, then the standard errors will be relatively larger, due to the smaller sample size.
Table 95 pct. confidence intervals, 2022-data:
Ability to make end meet
| Answer | Indicator | CI-lower limit | CI- upper limit |
|---|---|---|---|
| Very hard, hard | 11.3 | 10.4 | 12.3 |
| Somewhat hard | 17.7 | 16.6 | 18.8 |
| Somewhat easy | 28.2 | 27.0 | 29.4 |
| Easy | 25.8 | 24.7 | 26.9 |
| Very easy | 17.0 | 16.0 | 17.9 |
Non-sampling error
The response rate is about 40 per cent. This does leave a risk of bias as certain groups got lower response rates than others. The survey is calibrated to match the population on age and income, but there may still be an underrepresentation among immigrants, sick people .
Persons living in institutions or prisons and the homeless are not included in the survey. The exclusion of these groups probably results in underestimation of social exclusion.
The target population is "persons living in Denmark". This is the population directly or indirectly referred to in publications. The survey population differs from this by only including "persons living in private households in Denmark". Thus, persons living in institutions or prisons and the homeless are not included in the survey. Addresses with more than 10 adults and respondents who answer that they don't live in a private household are excluded from the survey. The exclusion of these groups probably results in underestimation of social exclusion. The survey population is defined by Eurostat and is hence the same in all countries.
Statistics Denmark use the Selected respondent model. Thus only one person answers the interview and his answers on household level questions are used to characterize the entire household. The majority of "Under 20 year olds" are children living at home.
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 survey in mostly compliant with Eurostat standards on data quality and timeliness. However the sample size is rather small and the response rates are low. Thus users have to be aware of statistical uncertainty, especially when analyzing results on minor sub-populations.
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
SILC is revised following validation by Eurostat. Following the national publication, which is based on structural data, longitudinal data are sent to Eurostat, where they are validated. After this validation, there is a correspondence between Eurostat and Statistics Denmark, which can lead to corrections in various places in the basic data. This can lead to changes in both data and weights, which can lead to minor changes in the published figures.