Map Intersection Based Merging Schemes for Administrative Data Sources and an Application to Germany

摘要

In many situations the applied researcher wants to combine different data sources without knowing the exact link and merging rule. This paper introduces a theoretical framework how two different regional administrative data sources can be merged. It presents different merging schemes based on the area size of intersections between both regional entities. Estimates of intersection areas are derived from a digital map intersection. The theoretical framework derives conditions for the unbiasedness of estimated intersections and merging rules. The paper also presents conditions under which the choice of merging rule does not matter and illustrates the theoretical results with a simulation study. An application to German counties and federal employment office districts illustrates the applicability of the approach. It delivers merging schemes for regional data sources of the federal German statistical office and of the federal German employment office.