Visit GESIS homepage
MISSY: Homepage aufrufen
Metadata for Official Statistics

Please select a study

Study: MZ 2021

Additional Programs

  • Questions on health and smoking habits
  • Additional information on economic activity (I) (shift work)

Ad-hoc-module EU Labour Force Survey

  • Migration and Job Market

Methodical Notes

Comparability over time

As of survey year 2021, in addition to the Labour Force Survey (LFS), which has already been integrated since 1968 and the Survey on Income and Living Conditions (SILC), which has been integrated since 2020, the survey on the use of Information and Communication Technologies in private households (ICT) is also integrated into the Microcensus. However, information from the ICT part will only be integrated into the Microcensus Scientific Use File from survey year 2022. Due to fundamental methodological changes and limitations in the quality of the Microcensus from 2020 onwards, comparability with previous years is limited, even if the unit non-response rate in 2021 is lower at approx. 14% than in 2020 at approx. 35%. Further information on this issue can be found in the metadata reports. Information on changes in the variables compared to the previous year can be found in the Data Manual. The variable time point matrix gives additional guidance on the comparability over time of variables in the Microcensus as of 1973.

Methodology of linking

After the change in subsampling starting with the SUF 2012 and with the provision of longitudinal consistent status numbers, it is possible to independently generate panel data sets with the MZ-SUFs. As a result of the renewal of the entire Microcensus sample in 2016, merging of cross-sectional data from 2012 survey are only possible up to and including the 2015 data. Due to the further development of the Microcensus in 2020, merging of cross-sectional data from 2016 are only possible up to and including 2019.

To make longitudinal analyses easier, the following identifiers are included in the data since 2015: idpers (longitudinal personal identifier), idpersx (cross-sectional personal identifier), idhh (longitudinal household identifier), idhhx (cross-sectional household identifier). As of 2020, the identifiers idawb (longitudinal sampling district identifier) and idawbx (cross-sectional sampling district identifier) are also included.


Changes In Typification

A number of typifications are no longer included to simplify data preparation since 2015. The report "Einführung in die eigenständige Erstellung von Typisierungen am Beispiel des Mikrozensus Scientific Use Files 2014" (Börlin 2020) shows how these typifications can be created using the data available in the data, using the example of the Microcensus SUF 2014.


The regional details federal state (Bundesland) and a rough classification of the community size classes (Gemeindegrößenklassen) are included in the Scientific Use File (SUF). With the help of the variable community size class, it is possible to distinguish between West and East Berlin.
The other variables in the SUF are also coarsened if necessary, so that each value in the univariate distributions comprises at least 5,000 persons from the target population.
The values of the variables on nationality and country of birth are aggregated in such a way that each category in the target population comprises at least 50,000 inhabitants.
The SUF is a de-facto anonymised 70% sample. Until 2011, the sampling units were households or apartments where all persons in a selected household or apartment were included in the subsample. From 2012 onwards, the sampling districts within a rotational quarter are used as sampling units for the subsample. This, together with longitudinal consistent identifiers, makes it possible to independently generate panel data sets with the Scientific Use Files.

Year Specific Documentation

The Metadatenreport Teil I Statistik and Metadatenreport Teil II zum Scientific Use File contain the information on this website as well as further details on the Microcensus SUF 2021.

Cross-sectional Data

Sampling Units


Achieved Sample Size


Units Of Observation

  • Persons (in private households and collective dwellings)
  • Households
  • Dwellings

Units Of Analysis

  • Persons
  • Living arrangements
  • Families
  • Households
  • Dwellings

Date of Data Collection

01.01.2021 - 31.12.2021

Participation Mandatory


Interview Mode - Description

Until and including 2019, the survey data were generally conducted orally (face-to-face) by interviewers from the state statistical offices. Additionally, part of the respondents completed a self-administered questionnaire or participated via telephone interview. Since 2020, the survey has been conducted increasingly by methods without face-to-face contact. This applies particularly to the new option of participating in the survey by using an online form (Computer Assisted Web Interview (CAWI)), which was introduced in 2020.
Proxy interviews are also permitted, i.e. an adult member of the household may answer on behalf of other members of the household.

Design Weight: Target

Dwelling, Household, Persons

Design Weight: Method

The Microcensus is designed as a single-stage, stratified cluster sample with a uniform sampling fraction for all strata. Area-based sampling districts serve as selection units. The selection is based on mathematical-statistical random procedures. A sampling fraction of 1 % is to be realized annually.
Also in the survey years from 2020 onwards, various extrapolation factors are available, most of which are used for households and persons alike and are scaled to the total resident population. The extrapolations are based on various demographic parameters, such as age groups, gender, nationality, and regional distribution. The annual extrapolation factors tend to include more parameters than the quarterly extrapolation factors. Detailed information on the parameters to which the extrapolation factors are adjusted at various regional levels can be found in Schmidt and Stein 2021. Due to the different subsamples available in the data since 2020, more extrapolation factors are available than before.
The SUF contains extrapolation variables that can be used to extrapolate to the total population without additional multiplication (by 1000). The extrapolation factors in the MZ-SUF are scaled by dividing all extrapolation factors in the entire MZ by 0.7. This scaling results in minimal deviations between results of the MZ-SUF and the published results. Further information on the extrapolation factors can be found in the Metadatenreport Teil I Statistik and the Metadatenreport Teil II zum Scientific Use File.