Study: MZ 2005
Additional Programs
- Health (Sampling Fraction: 1% )
- Private and employers´ pension schemes (Sampling Fraction: 1% )
- Additional information on economic activity (I) (Sampling Fraction: 1% )
- Additional information on migration (Sampling Fraction: 1% )
Ad-hoc-module EU Labour Force Survey
- Reconciliation between work and family life (Sampling Fraction: 0.1% )
Changes In Questionnaire
- Variables discontinued after the 1996-2004 survey programme:
- Year of marriage
- Current attendance at kindergarten, day nursery, crèche
- Usual and actual working week in days
- Change of employer (Betriebswechsel)
- Dependency on nursing care
Methodical Notes
Implementation
- Continuous survey spread over the year. Sample randomly divided into 48 weekly parts (interviewer packages). Weekly parts divided into 12 equal monthly volumes, thereby spreading the sample uniformly over the year. Smaller, more professional team of interviewers. Computer-assisted personal interviewing (CAPI) using laptops.
- Moving reference week
- Quarterly and annual average results
Sampling fraction
- Microcensus and EU Labour Force Survey variables: uniformly 1 %
- Ad hoc modules of the EU Labour Force Survey: 0.1 %
Sampling technique
Before drawing the sample, the sampling districts are arranged by regional subdivision (i.e. within each stratum they are sorted hierarchically by regional stratification group, county (Kreis), municipality size class (Gemeindegrößenklasse), municipality (Gemeinde), and sampling district number).
- The sampling frame is divided into 100 one percent samples: Each 100 consecutive sampling districts ("zones") are assigned a random permutation of the numbers 0 to 99.
- The sampling frame is divided into four rotation quarters of 0.25% each. Each quarter comprises four consecutive zones and is allocated a random permutation of the numbers 1 to 4.
- The sampling frame is divided into 48 "weekly parts".
- The 48 weekly parts are divided into 12 monthly volumes of 4 parts each (thereby spreading the sample uniformly over the year).
- The 1% sample is randomly divided into twelve equal sub-samples (thereby spreading the sample uniformly over the year).
Extrapolation / Weights in the Scientific Use File
- Extrapolation is based on a two-stage procedure: (1) First, household non-response is corrected for using compensation factors based on information about these households. (Unit non-response in the 2005 Microcensus was approx. 6% of households and 4% of individuals). (2) The sample values weighted with these compensation factors are then adjusted to conform in terms of age, citizenship, and sex to benchmark figures from the intercensal population estimates (laufende Bevölkerungsfortschreibung) and the Central Register of Foreign Nationals (Ausländerzentralregister). The source of the benchmark figures for temporary-career volunteers (Zeitsoldaten) and regulars (Berufssoldaten) with the German Armed Forces, members of the Federal Police and the Bereitschaftspolizei (riot police), and persons doing military service is the inventory data of the Federal Ministry of Defence, the Federal Ministry of the Interior, and the Federal Police.
- Adjustment takes place on a quarterly basis at regional level.
- Since 2005, the same extrapolation factors are available for all members of a household. The Scientific Use File contains the extrapolation variables from the original Microcensus file for quarterly analyses, annual averages, and the EU-LFS sub-sample (annual average).
Extrapolation
- New adjustment data and variables:
- Age * Sex (intercensal population estimates)
- Citizenship * Sex (intercensal population estimates and Central Register of Foreign Nationals)
- Population by month (intercensal population estimates)
- New procedure: Generalized regression estimation for separate adjustment to marginal distributions
- Same extrapolation factors for all members of a household
New Concepts
- Concept of living arrangements in order to capture consensual unions (cohabitations)
- Kinship ties between household members
- Household reference person: Main income earner
- Note: In the 2005 and 2006 Microcensuses, the federal states (EF1) are coded in alphabetical order; in the MCs up to 2004 and from 2007 onwards, codes are allocated in accordance with the official municipality key (amtlicher Gemeindeschlüssel).
- In analyses by part of the country, the statistical offices usually no longer distinguish between the former territory of the Federal Republic including West Berlin and the new federal states including East Berlin but rather between the former territory of the Federal Republic without Berlin and the new federal states including Berlin. This is because, following a territorial reform, the former East-West division of Berlin can no longer be clearly represented (see here in German).
Year Specific Documentation
- Microcensus Scientific Use File 2005 Documentation and Data Preparation [in German] [.pdf]
Cross-sectional Data
Sampling Units
Districts
Achieved Sample Size
477239
Units Of Observation
- Persons (in private households and collective dwellings)
- Households
Units Of Analysis
- Persons
- Families
- Households
Start Date
01-01-2005
End Date
31-11-2005
Participation Mandatory
Yes
Percentage Of Proxy Interviews
25.05 %
Design Weight: Target
Dwelling, Household, Persons
Design Weight: Method
The Microcensus is a single-stage, stratified cluster sample with a uniform sampling fraction for all strata. As a rule, the sampling fraction is 1 %; it applies to all sampling units (dwellings, households, persons).
Because the selection probability of the Scientific Use File (SUF) basically remains constant at 70%, design weights can be created on the basis of the inverses of the sampling fractions of the Microcensus (1 %) and the Scientific Use File (70 %): w = 1 / (0.01 * 0.7).
Non-response Weight: Method
In the Microcensus, as in all surveys, the sampling plan cannot be realised fully. Hence, undercoverage occurs in the form of non-response on the part of the households to be surveyed. Because households and their members are obliged by law to provide information for the Microcensus, non-response is due mainly to the fact that households could not be reached during the survey. Cases of non-response are corrected using the information that is available about the non-responding households.
Since 2005, the compensation factors are no longer calculated by dividing target figures by actual figures but rather by means of generalised regression estimation (calibration technique). At regional level, the following characteristics, or combinations of characteristics, are taken into account for private households: rotation quarter and new-construction stratum (federal state), 19 compensation classes (see above; regional adjustment stratum), and total private households (regional subgroup). For collective dwellings: number of persons in collective dwellings (regional subgroup).
Coverage Adjustment Weight: Method
In contrast to compensation, adjustment is carried out at person level.
Since 2005, adjustment has no longer been carried out at the level of disjointed adjustment strata but rather on a quarterly basis at different regional levels; data from the Central Register of Foreign Nationals (Ausländerzentralregister) are also used. Moreover, the same extrapolation factors are available for all members of a household. The extrapolation terms and regional units are: age groups x sex; nationality groups x sex; population group (temporary career volunteers and regular soldiers including members of the Federal Police and the Bereitschaftspolizei (riot police), persons doing military service, civilian population) (federal state); nationality groups x sex (administrative district); total population (regional adjustment stratum).
Final Weighting: Method
For the final weight a two-stage procedure is employed: In a first step the net sample of the successfully interviewed households is adjusted to the gross sample of all households to be interviewed (compensation). In a second step this gross sample is benchmarked to the update of the current population figures (adjustment). The final weights result from a combination of this two-stage procedure of compensation and adjustment. They are derived from the original data. In order to weight for the population it is necessary to multiply with the inverse value of the selection probability of the Microcencus (1%). This equates to a multiplication of the weighting factors by 1000/0.7.
From 2005 onwards, in addition to the standard extrapolation factors for annual average values there are also extrapolation factors for quarterly analyses and for the ad hoc modules and structural variables of the EU-LFS. Moreover, there are special extrapolation factors for supplementary programmes of the Microcensus (e.g., on the housing situation).
See [.pdf] (in German)