Page 15 - Invited Paper Session (IPS) - Volume 1

IPS30 Stefan D. et al.
Figure 2: The German Census Model in 2011 from Bechtold (2016)

• The supplementary household sample survey, covering almost 10 percent
of the population

was used to adjust the register data in municipalities with 10,000 inhabitants
or more, after the registers have been corrected for multiple residences. For
the calculation of the population of large municipalities, the level of error of
the population registers (over- and under-coverage) detected by the
household survey was taken into account. The sample was designed to ensure
that the population figures of large municipalities meet an error margin of 1
percent target at a 95 percent confidence level. The method applied to
optimise the sampling process was dedicated individually to each municipality
and the sample size ranged between 2.1 percent and 45.6 percent and differed
significantly even for municipalities of a similar size. For municipalities with
less than 10,000 inhabitants, a survey was carried out among those households
that had been identified as needing clarification by comparing results of the
survey of buildings and dwellings and the population registers.
In addition to the objective to establish the population figures, the
supplementary household survey was also used to cover further compulsory
census variables of the EU that are not available from registers (in particular
the labour market participation and the educational attainment). The
additional census topics were collected in all municipalities (not just those with
10,000 inhabitants or more). The sample size was designed to allow
publications at NUTS-3 level.
• For persons living in special facilities, e.g. a communal accommodations, care
institutions, dormitories or similar types of living quarters, census information

4 | I S I W S C 2 0 1 9