Recovering localised information on agricultural structures while observing data confidentiality regulations – the potential of different data aggregation and segregation techniques

RAUMIS, a modelling and information system used in policy impact assessments, can be used to measure the impact of agriculture on the environment. County-level resolution often limits the analysis, and further disaggregation at the municipality level would reduce aggregation bias and improve the assessment. Although the necessary data exist in Germany, data protection regulations (DPRs) prohibit its direct use. By obtaining the locally weighted averages and aggregating individual production activities into larger groups, aggregated data at the municipality level can be made available. The aggregation reduces the information content and introduces additional error. The goal of this study was to determine the necessary amount of information to estimate Germany-wide production activities at the municipality level while ascertaining compliance with the DPR. We applied the highest posterior density estimation and tested different prior information content at the municipality level. The results indicated that the proposed approach can be used to adequately estimate most activities without violating the DPR.

[1]  Arnold Zellner,et al.  An Introduction to Bayesian Inference in Econometrics. , 1974 .

[2]  Jozsef Kiss,et al.  Dispersal kernels of the invasive alien western corn rootworm and the effectiveness of buffer zones in eradication programmes in Europe , 2010 .

[3]  David A. Elston,et al.  Research Article: Estimating local variations in land use statistics , 2003, Int. J. Geogr. Inf. Sci..

[4]  Douglas J. Miller,et al.  Maximum entropy econometrics: robust estimation with limited data , 1996 .

[5]  Bernhard Osterburg,et al.  Auswertung von Daten des Integrierten Verwaltungs- und Kontrollsystems zur Abschätzung von Wirkungen der EU-Agrarreform auf Umwelt und Landschaft , 2009 .

[6]  Torbjörn Jansson,et al.  A BAYESIAN ALTERNATIVE TO GENERALIZED CROSS ENTROPY SOLUTIONS FOR UNDERDETERMINED ECONOMETRIC MODELS , 2008 .

[7]  W. Britz,et al.  Eu-Wide Farm Types Supply In Capri - How To Consistently Disaggregate Sector Models Into Farm Type Model , 2010 .

[8]  P. Verburg,et al.  Downscaling of land use change scenarios to assess the dynamics of European landscapes , 2006 .

[9]  Andrew Moxey,et al.  Areal Interpolation of Spatially Extensive Variables: A Comparison of Alternative Techniques , 1994, Int. J. Geogr. Inf. Sci..

[10]  Thomas Heckelei,et al.  A Statistical Approach for Spatial Disaggregation of Crop Production in the EU , 2005 .

[11]  Liangzhi You,et al.  An entropy approach to spatial disaggregation of agricultural production , 2006 .

[12]  Alexander Gocht,et al.  EU-wide farm type supply models in CAPRI—How to consistently disaggregate sector models into farm type models , 2011 .

[13]  Markus Kempen,et al.  Linking an economic model for European agriculture with a mechanistic model to estimate nitrogen and carbon losses from arable soils in Europe , 2008 .

[14]  Patrick Bogaert,et al.  A statistical method to downscale aggregated land use data and scenarios , 2006 .

[15]  Josep Domingo-Ferrer,et al.  Statistical Disclosure Control , 2012 .

[16]  A. Zellner.  An Introduction to Bayesian Inference in Econometrics , 1971 .

[17]  Dietmar Roßberg,et al.  Definition von Boden-Klima-Räumen für die Bundesrepublik Deutschland , 2015 .