Pilotstudie einer surveybasierten Verknüpfung von Personen- und Betriebsdaten : Durchführung sowie Generierung einer Betriebsstudie als nachgelagerte Organisationserhebung zur SOEP-Innovationsstichprobe 2007

In this paper, we compare different approaches to the generation of datasets linking employees and firms, and present the specific advantages and disadvantages of each method. We discuss in detail the employee-first method, which has only been investigated so far in the survey research in initial US studies. We show that for Germany, this method provides reasonably comprehensive and error-free data on individuals. Our analyses are based on the results of a follow-up study of firms that was first tested in a SOEP Pretest in the year 2007 on more than 300 employees. Our results also show that the data edition method provides a relatively easy means of considerably improving the quality of contact addresses obtained through an open-ended survey question. The quality and number of the firm contact data as well as the number of participating firms can be increased as well through improvements in the different phases of the generation process.