Metadata for Official Statistics

Calculating sampling error in the microcensus

Bernhard Schimpl-Neimanns

The following information describes how sampling error can be calculated for the microcensus scientific use files using both so-called free extrapolation (design weighting) and constrained extrapolation (post-stratification).


Net changes

The provision of longitudinal-consistent identification numbers from the 2012 microcensus onwards makes it possible to take the covariance over time resulting from the partial rotation of the primary units into account when estimating the variance of changes in characteristics between two points in time (net change). For the estimation of the covariance, the method proposed by Berger und Priam (2016) can be applied. In this paper, the implementation is tested for selected indicators of the microcensus. For the indicator "employment rate for 60- to 64-year-olds", the procedure is demonstrated for the statistical programmes.

  • Schimpl-Neimanns, B., 2019: Varianzschätzung von Nettoveränderungen mit dem Mikrozensus ab 2012. AStA Wirtschafts- und Sozialstatistisches Archiv. DOI 10.1007/s11943-019-00240-0

  • Statistical programms for the variance estimation of net changes from MZ 2012 onwards
    R SAS SPSS Stata
    net_et.R net_et.sas net_et.sps net_et.do

    Cross-sectional data

    The changeover of the microcensus to a continuous quarterly survey with a moving reference week from 2005 was accompanied by a modification of the procedures applied when extrapolating the sample results. Besides the relevant report Varianzschätzung für Mikrozensus Scientific Use Files ab 2005 (Variance estimation for microcensus scientific use files from 2005) further texts and example programs show estimates for the 1996-2004 and 1973-1987 Microcensuses.

    • Schimpl-Neimanns, B., 2010: Varianzschätzung für Mikrozensus Scientific Use Files ab 2005. GESIS-Technical Report Nr. 2010/03. [.pdf]
    • Schimpl-Neimanns, B., 2011: Schätzung des Stichprobenfehlers in Mikrozensus Scientific Use Files ab 2005. AStA Wirtschafts- und Sozialstatistisches Archiv 5 (1): 19-38. DOI: 10.1007/s11943-011-0092-4. [.pdf]

    • Programs for the construction of auxiliary variables for the microcensus from 2005 and examples from the GESIS-Technical Report 2010/03
      Complex Samples
      TR_10-03_SPSS.zip TR_10-03_SAS.zip TR_10-03_Stata.zip

    • Introduction: Calculating the sampling bias in the Microcensus [.pdf]
      • Design-based estimation of totals for the Scientific Use File of the Microcensus 1997 [.pdf]
      • Design-based estimation of totals for the Scientific Use File of the Microcensus 1996 [.pdf]
    • Schimpl-Neimanns, B., 2009: Schätzung des Stichprobenfehlers im Mikrozensus mit Stata – Eine Einführung mit Beispielen zum Campus File Mikrozensus 2002. GESIS-Methodenbericht 2009/02. Mannheim: GESIS. [.pdf]
    • R_Beispiele.zip SAS_Beispiele.zip SPSS_Beispiele.zip Stata_Beispiele.zip

    • Rendtel, U./Schimpl-Neimanns, B., 2001: Variance Estimation for the Scientific Use File of the German Microcensus, Paper prepared for the International Conference on Quality in Official Statistics, Stockholm, May 14-15, 2001. [.pdf]
    • Rendtel, U./Schimpl-Neimanns, B., 2001: Die Berechnung der Varianz von Populationsschätzern im Scientific Use File des Mikrozensus ab 1996. ZUMA-Nachrichten 48: 85-116. [.pdf]
    • Schimpl-Neimanns, B./Rendtel, U., 2001: SAS-, SPSS- und STATA-Programme zur Berechnung der Varianz von Populationsschätzern im Mikrozensus ab 1996. ZUMA-Methodenbericht 2001/04. [.pdf]
    • Schimpl-Neimanns, B., 2005: Berechnung des Stichprobenfehlers im Mikrozensus mit SPSS Complex Samples. [.pdf]

    • Programs for the calculation of the variance of … for the microcensus from 1996 to 2004
      Complex Samples
      Totals VarMZ_T.SAS VarMZ_T.SPS CS_T.SPS VarMZ_T.DO
      Ratios and means VarMZ_R.SAS VarMZ_R.SPS CS_R.SPS VarMZ_R.DO
      Regression estimators (adjustment) VarMZ_A.SAS VarMZ_A.SPS CS_A.SPS VarMZ_A.DO


      Programs for the calculation of the variance of ... for the microcensus from 1973 to 1987, using the 1987 Microcensus as an example
      Complex Samples
      Totals Total_MZ87.sas Total_MZ87.sps Total_MZ87.do
      Ratios Ratio_MZ87.sas Ratio_MZ87.sps Ratio_MZ87.do