For the purpose of academic teaching at universities and research institutes, the IAB has generated absolutely anonymised survey data of the “Panel Study ‘Labour Market and Social Security’ (PASS)”.
Two different PASS campus files (CFs) are available at the FDZ. The cross-sectional campus file (QFC) covers the cross-sectional data of the first wave of the PASS scientific use file and contains a wider range of variables than the second campus file. The longitudinal campus file (LFC) contains less variables but allows longitudinal analysis based on the waves 1-3 of the PASS scientific use file.
In the field of academic teaching, with both datasets different goals can be pursued. The cross-sectional campus file is suitable for an introduction on handling complex data structures (data management, data preparation, multilevel analysis etc.). The longitudinal campus file could be applied for the teaching of certain analysis techniques, e.g. analysing panel data.
The essential differences between the campus files and the scientific use file are:
- a reduced choice of datasets (cf. chapter 2.1, FDZ-Datenreport 06/2011)
- a reduced number of observations (cf. capter 2.2, FDZ-Datenreport 06/2011)
- a reduced range of variables, partially modified variable names and modified identification numbers (cf. chapter 2.3, annex 1 and annex 2, FDZ-Datenreport 06/2011)
- reduction of information, e.g. modification of categories, modification of the data on every level (cf. chapter 2.4, annex1 and annex 2, FDZ-Datenreport 06/2011)
A description of both campus files can be found in the FDZ-Datenreport 06/2011 (only in German). For detailed documentations on PASS (FDZ Datenreporte, questionnaires etc.), which are also relevant for analyses with the campus files, please refer to working tools.
Advice for data usage
The campus files have been specifically designed for the purpose of academic teaching and serve only for vivid and practical training of survey, data management or various other data analysis techniques applied to different social research problems. Due to the utilized comprehensive anonymisation techniques the data must not be used for any statistical inference concerning the contents or for any kind of publication (including seminar papers or bachelor theses). With this data it is not possible to make generalised statements about individual characteristics or relationships between different characteristics.
Only the scientific use file (SUF) may be used for valid substantial analysis. Information on the application procedure is available in the category ‘Data Access/Scientific Use File’.
Data access and dissemination