Access to microdata
The Research Data Centres provide different possibilities for the access to official microdata. They differ on-site- and off-site ways of access.
There are PC workplaces for guest researchers in all locations of both Research Data Centres (safe centre). These can be used by researchers to analyse microdata inside the safe premises of the statistical offices. As the data is already protected through the regulation of data access and the equipment of the pc workplace, the microdata at the safe centre can be provided factually or formally anonymised – depending on the sensitivity of the data.
The PC workplaces at which microdata can be analysed are equipped with the common statistical programs (SPSS, SAS, Stata and partly R). A separate PC workplace with internet connection is available for e-mail communication and internet searches. Several visits of a safe centre can take place within the scope of one project. Appointments have to be made in advance with the supervising RDC.
For the use of a safe centre it is required that all users are able to write program code in at least one analysis program offered at the RDC.
When using remote execution, the data user has no direct access to the data. The users rather receive data structure files which resemble the original material with regard to structure and variable values. With the help of these files, program codes can be prepared using the statistical programs SPSS, SAS, Stata or partly R. These program codes are applied by staff of the statistical offices to analyse the original data. The data users receive the results of those analyses after the relevant confidentiality checks.
Via remote execution, formally anonymised microdata – can be analysed. Several program codes can be submitted within the scope of one project.
For the use of remote execution it is required that all users are able to write program code in at least one analysis program offered at the RDC.
Scientific Use Files (SUF) are standardised datasets which are generated by the Research Data Centres for popular statistics. Because of the factual anonymization of the microdata, they may be used outside the safe premises of the statistical offices. Compared to the on-site ways of access, SUF offer a lower potential for analyses. However, they are designed in a way that makes them suitable for a large part of scientific projects.
SUF are offered for the analysis programs SAS, SPSS and Stata or are provided with the according input routines. They may only be used within the scientific institution that requested the data.
Due to legal restrictions, SUF may only be used by researchers who are employed by a research institution that is registered and located in Germany. The use of Scientific Use Files may only take place in Germany. Researchers from foreign institutions are asked to use remote execution or to work at a safe centre.
Public Use Files (PUF) contain absolutely anonymised microdata – and. Because of the strong anonymization, only selected variables are available. Variables with a high degree of subject-related detail are aggregated. Detailed regional breakdowns can usually not be made on the basis of Public Use Files.
PUF are offered for the analysis programs SAS, SPSS and Stata or are provided with the according input routines. Their use is not bound to a specific place of use.
The Research Data Centres of the Federal Statistical Office and the Statistical Offices of the federal states encourage the use of official microdata in university teaching. Thus, they offer Campus Files which are designed specifically for teaching. They contain absolutely anonymised microdata – which students can use to acquire methodological knowledge and gain first experiences in analysing official microdata.
Campus Files are offered for the analysis programs SAS, SPSS and Stata. They can be downloaded for free after successful registration. An overview on the available Campus Files – can be found on the summary page.
Combined ways of access
The described ways of access can also be combined freely. It is, for example, often useful to combine work at a safe centre and remote execution. Especially for longer research projects, a combination like this is often reasonable. Using combined ways of access usually results in extra costs.
Non-scientific use of data
According to section 16 (6) of the Federal Statistics Law (BStatG), the Research Data Centres may only grant “institutions of higher education or other institutions entrusted with tasks of independent scientific research” access to official microdata. Persons or institutions that are not covered by this definition can contact the enquiry services of the respective Statistical Offices of the Federation and the Federal States. The contact information can be found in the following overview (German version):