Title: German Socio-Economic Panel (SOEP), data of the years 1984-2014
DOI: 10.5684/soep.v31.1
Collection period: 1984-2014
Publication date: March 18, 2016
Principal investigators: Jürgen Schupp, Jan Goebel, Martin Kroh, Carsten Schröder, Klaudia Erhardt, Alexandra Fedorets, Marco Giesselmann, Markus Grabka, Peter Krause, Simon Kühne, Maximilian Priem, David Richter, Rainer Siegers, Paul Schmelzer, Christian Schmitt, Daniel Schnitzlein, Ingrid Tucci, Knut Wenzig
You can see the complete information by clicking at the DOI of the original data set
http://dx.doi.org/10.5684/soep.v31
Data set information:
Number of units | 104,320 |
Number of variables | 57,670 in 396 data sets |
Data format | STATA, SPSS, SAS, CSV |
MD5 fingerprints
1. Changes due to the integration of the FiD study
As you already know, data release v31 includes the complete data from “Familien in Deutschland” (Families in Germany, FiD), which is being retrospectively integrated into the SOEP and made available in user-friendly form to all SOEP users. The survey was carried out in parallel to the SOEP as a so-called “SOEP-related study” from 2010 to 2013.
Starting with Version 31 of the data, the FiD sample has been integrated completely into SOEP-Core—that is, as if it were a new sample drawn as part of SOEP-Core in 2010 and 2011. This means that in the data from 2010 on, SOEP users “automatically” have more cases in their study population without having to make any changes in scripts.
In total, 14,166 variables from 64 datasets have been integrated into the various SOEP datasets, and the generated datasets or variables have been adjusted. Variables in the FiD survey instruments that were not contained in the corresponding SOEP survey instruments have been included in the respective datasets as additional variables (with the original FiD variable names starting with “fyy”, where “yy” is a two-digit year identifier).
1.1. Household questionnaire:
1.2. Individual questionnaire:
1.3. Derived calendar information
We were able to integrate additional variables in the calendar files: This applies to the variables on military or community service as well as alimony or child support. The affected variables are:
1.4. B[A-D]HBRUTTO: Household gross data
The variables containing the BBSR spatial planning category, differentiating between rural and urban regions, are updated and generated for the additional FiD cases. The affected variables are:
1.5. KIND/KIDLONG: Person-related variables on children (up to the age of 16) within the household
1.6. Imputed monthly household income: MIHINC and I$HINC in $HGEN
All waves affected by the integration of FiD (2010 [BA] - 2013 [BD]) were completely newly imputed. With the new imputations, we now provide the imputed household income generated by only one imputation model and have also generated 10 implicates for the MIHINC dataset (FiD only provided 5 implicates).
1.7. $PEQUIV: CNEF variables with extended income information for the SOEP
Since no equivalent files were generated with the FiD data release, and especially since there were no data on the previous year’s household income or simulated tax and social insurance contributions, all $EQUIV from 2010-2013 had to be generated again for SOEP.v31.1.
The data provided in v31.1 now contain harmonized imputations and simulations for all SOEP subsamples including the newly integrated FiD samples.
2. Other changed variables
2.1. BIOCOUPLM/Y, BIOMARSM/Y and $FAMSTD in $PGEN:
Changes within the couple history files BIOCOUPLM and BIOCOUPLY, marital history files BIOMARSM and BIOMARSY, and variable marital status of the survey year ($famstd) in $PGEN:
2.2. BIOEDU: Biographical data on educational participation and transitions
Variable persnr (personal id) had the value 0 for all observations. In the new update, we have fixed this problem.
2.3. BEPBRUTTO: Gross data, individual level
The previous year’s identifiers had not been correctly implemented in the individual gross data set. This has been corrected. Affected variables:
2.4. HEALTH: SOEP health module in the individual questionnaire
The dataset was unfortunately corrupted by mistake in our database. This has been corrected in v31.1.
2.5. BEPGEN: Genereated variables, individual level
2.6. $HGEN: Generated Variables, household level
The SOEP micro data which we make available for scientific research can only be interpreted using statistical software. Direct use of SOEP data is subject to the high standards for lawful data protection in the Federal Republic of Germany. Signing a contract on data distribution with the DIW Berlin is therefore a precondition for working with SOEP data. After signing the contract, the data of every new wave will be available on request.
more information
Dokumentationen der generierten Variablen (ZIP, 5.02 MB) (einschließlich der Biografie-Datensätze)
Item-Korrespondenzlisten als Excel-Dateien (klassische Basisdatei, mit ausschl. deutschen Labels, mit ausschl. englischen Labels)
Dokumentation von SOEPlong
Das SOEP verfügt über eine detaillierte Dokumentation der Erhebung und der generierten Daten, Details finden Sie hier.
Überblick über versionsspezifische Neuerungen am Datensatz