• To improve the measurement of ILO labour force status, in particular, the fieldwork and some questions relating to labour market participation have undergone changes since 2005. Compared to the 2008 Microcensus, some questions in the 2009 round are worded differently, or have different response categories. Hence, distribution differences may be due to labour market changes or they may be due to the modification in the method (new questions). This concerns the following core questions for the determination of the respondent's ILO labour status:
  • EF77: Paid employment (reference week)
  • EF78: Parental leave, (special) leave or the like (reference week)
  • EF80: Other paid employment
  • EF225: Registered with the Agentur für Arbeit (Federal Employment Agency)

• The extrapolation factor EF957 is available for analyses of disability data (EF465, EF466). It can be used to compensate for item non-response and systematic differences between the disability data and official statistics on people with severe disabilities. In the case of persons with an officially certified disability (EF465=1-3), the Microcensus data at federal level were adjusted to the results of the official statistics on people with severe disabilities. The extrapolation framework comprises the following variables: Degree of disability (up to 49 % / 50 % or more), Age groups (disability of up to 49 %: up to 24 years / 25-49 / 50-59 / 60-79, 80 years and over; disability of 50 % or more: up to 14 years/ 15-29 / 30-44 / 45-59 / 60-79 / 80 years and over), and Sex.
• In the 2009 Microcensus – in contrast to the 2008 round – the mode of data collection (EF7) and the differentiation between pupils and non-pupils were used to estimate response probabilities when constructing the extrapolation factor EF956 for the variables of the EU Labour Force Survey (EU-LFS) ad hoc module. Because the target population of the ad hoc module was persons between the ages of 15 and 34, person factors rather than household factors were calculated.
• And finally, in the 2009 Microcensus Scientific Use File the coding of missing values was adapted to standards of social science data analysis and documentation (see, for example, ICPSR 2009). In the original data, missing values are not differentiated as a rule, nor are they shown separately with numeric values. Rather, they are coded as blank and are therefore treated as so-called system-missing values by the data analysis programmes. In the Scientific Use Files up to 2008, this procedure was followed to a large extent. However, numeric values (for example, "9" or "99"), which are used in statistical packages to declare user-defined missing values, were assigned. In the 2009 Microcensus Scientific Use File, missing values are retrospectively differentiated by individual reason or sub-population and are shown with specific negative values:
  • -1 Not applicable (Collective household)
  • -2 Not applicable (Non employed)
  • -3 Not applicable (Person under 15 years of age)
  • -4 Not applicable (Not in subsample: LFS structural variables, ad hoc module)
  • -5 Not applicable (Specific situations where the respondent has been routed away from the question by a filter)
• The only exceptions are a few multiple-response variables. For example, the individual response options to Question 73 (EF254-EF259) about efforts to find a job (or another job) in EF254 "Seeking work: Federal Employment Agency (Agentur für Arbeit)(during the last 4 weeks), paid employment" are coded as "1" if the respondent answers "Yes", and otherwise as "0". Hence, the residual category "0" covers "No" and "Not applicable (…)".

• Since 2008, the revised Statistical Classification of Economic Activities, NACE Rev. 2, has been used as a rule in the EU Labour Force Survey. The correspondingly updated German version of the classification, the 2008 edition of the Klassifikation der Wirtschaftszweige (WZ 2008), has been applied in the German Microcensus since 2009 (see EF137, EF105, EF214, EF445, EF737, EF825 and EF849). A conversion key from WZ 2003 to WZ 2008 was developed with the help of double coding according to WZ 2003 and WZ 2008 in the 2009 round of the Microcensus (January to April) and further estimates. The Scientific Use File contains a classification according to the WZ03 (variable EF120) that is comparable to EF137.

• In this context, further changes were made to the classification of labour force status in the 2009 round of the Microcensus:
  • When delineating "non-employed persons" (Nichterwerbstätige) (EF29 and EF38), registration with the Federal Employment Agency or other authorities as unemployed or seeking work (EF232=1-2) is no longer taken into account.
  • In the case of labour status as defined by Eurostat (EF39), persons who were not at work and who do not have a job (EF38=9) have been classified as unemployed since 2009 (EF39 = 4). Up to 2008, this group was assigned to the "economically inactive persons" (Nichterwerbspersonen) category (EF39 = 6)

Microcensus Scientific Use File 2009 Documentation and Data Preparation [in German] [.pdf]

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

• Persons
• Living arrangements
• Families
• Households

01-01-2009

31-12-2009

Yes

• 75.8 % CAPI
• 20.5 % CATI
• 3.7 % Self-administered

24.62 %

Dwelling, Household, Persons

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 inverse of the sampling fraction of the Microcensus (1 %) and the Scientific Use File (70 %): w = 1 / (0.01 * 0.7).

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).

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).

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, are already multiplied with the inverse of the selection probability and extrapolated to 1000 of the population.

From 2005 onwards, in addition to the standard weighting factors for annual averages there also exist weighting factors for the quarterly samples, for the ad hoc modules and structural variables of the EU-LFS. Moreover, there are special weighting factors for supplementary programmes of the Microcensus (e.g., on the housing situation).

See [.pdf] (in German)