Advances in Business Statistics, Methods and Data Collection

22Statistical Data Production in a Digitized Age: The Need to Establish Successful Workflows for Micro Data Access

Stefan Bender^{1, 2}, Jannick Blaschke¹, and Christian Hirsch¹

¹Data Service Center, Deutsche Bundesbank, Frankfurt, Germany

²School of Social Science, University of Mannheim, Mannheim, Germany

22.1 Introduction

Nowadays, empirical researchers and statisticians find themselves in a curious situation. On the one hand, data are everywhere and come from an ever‐increasing number of different sources. Researchers use more data they no longer directly collect themselves (e.g. via surveys). Instead, they often analyze organic data (Groves 2011) collected for other purposes that are now being reused, e.g. via ETL¹ or an adapted version of the Total Survey Error Approach (Biemer et al. 2017; Amaya et al. 2020). Many chapters in this book are evidence of how fundamentally the emergence of these new data sources has transformed the practice of social science research.

On the other hand, a surprisingly large amount of relevant data remains hidden in tightly regulated silos, which means they are underexploited by empirical research and statistics (e.g. SVR‐Gutachten 2021). One reason lies in the nature of the data themselves, which oftentimes allow the disclosure of information about an individual person's health or a company's business model. Initiatives like the FAIR data principles (Wilkinson et al. 2016; European Commission 2018) or the reproducibility standards of the AEA ...